Daily Papers

As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications, whether accidental or intentional, becomes critical to minimize risks. However, there is no standard approach to evaluate tamper resistance. Varied data sets, metrics, and tampering configurations make it difficult to compare safety, utility, and robustness across different models and defenses. To this end, we introduce TamperBench, the first unified framework to systematically evaluate the tamper resistance of LLMs. TamperBench (i) curates a repository of state-of-the-art weight-space fine-tuning attacks and latent-space representation attacks; (ii) enables realistic adversarial evaluation through systematic hyperparameter sweeps per attack-model pair; and (iii) provides both safety and utility evaluations. TamperBench requires minimal additional code to specify any fine-tuning configuration, alignment-stage defense method, and metric suite while ensuring end-to-end reproducibility. We use TamperBench to evaluate 21 open-weight LLMs, including defense-augmented variants, across nine tampering threats using standardized safety and capability metrics with hyperparameter sweeps per model-attack pair. This yields novel insights, including effects of post-training on tamper resistance, that jailbreak-tuning is typically the most severe attack, and that Triplet emerges as a leading alignment-stage defense. Code is available at: https://github.com/criticalml-uw/TamperBench

As the development of large language models (LLMs) rapidly advances, securing these models effectively without compromising their utility has become a pivotal area of research. However, current defense strategies against jailbreak attacks (i.e., efforts to bypass security protocols) often suffer from limited adaptability, restricted general capability, and high cost. To address these challenges, we introduce SafeAligner, a methodology implemented at the decoding stage to fortify defenses against jailbreak attacks. We begin by developing two specialized models: the Sentinel Model, which is trained to foster safety, and the Intruder Model, designed to generate riskier responses. SafeAligner leverages the disparity in security levels between the responses from these models to differentiate between harmful and beneficial tokens, effectively guiding the safety alignment by altering the output token distribution of the target model. Extensive experiments show that SafeAligner can increase the likelihood of beneficial tokens, while reducing the occurrence of harmful ones, thereby ensuring secure alignment with minimal loss to generality.

Safety aligned Large Language Models (LLMs) are vulnerable to harmful fine-tuning attacks qi2023fine-- a few harmful data mixed in the fine-tuning dataset can break the LLMs's safety alignment. Existing mitigation strategies include alignment stage solutions huang2024vaccine, rosati2024representation and fine-tuning stage solutions huang2024lazy,mukhoti2023fine. However, our evaluation shows that both categories of defenses fail when some specific training hyper-parameters are chosen -- a large learning rate or a large number of training epochs in the fine-tuning stage can easily invalidate the defense, which however, is necessary to guarantee finetune performance. To this end, we propose Antidote, a post-fine-tuning stage solution, which remains \textit{agnostic to the training hyper-parameters in the fine-tuning stage}. Antidote relies on the philosophy that by removing the harmful parameters, the harmful model can be recovered from the harmful behaviors, regardless of how those harmful parameters are formed in the fine-tuning stage. With this philosophy, we introduce a one-shot pruning stage after harmful fine-tuning to remove the harmful weights that are responsible for the generation of harmful content. Despite its embarrassing simplicity, empirical results show that Antidote can reduce harmful score while maintaining accuracy on downstream tasks.Our project page is at https://huangtiansheng.github.io/Antidote_gh_page/

Large Vision-Language Models (LVLMs) have made significant strides in multimodal comprehension, thanks to extensive pre-training and fine-tuning on large-scale visual datasets. However, despite their robust textual safety mechanisms, they remain vulnerable to harmful visual inputs. Existing safeguards-typically relying on pre-filtering or fine-tuning-incur high costs and diminish overall utility. To address this critical vulnerability, we introduce SafeCLIP, a lightweight method that leverages LVLMs inherent multimodal alignment for zero-shot toxic image detection. By projecting CLIPs discarded CLS token into its text space and matching it with toxic descriptors, SafeCLIP detects harmful content without any architectural changes-adding minimal latency and enabling dynamic safety corrections during inference and fine-tuning.Experiments show that SafeCLIP achieves a 66.9% defense success rate with only 3.2% false positive rate and 7.2% overhead. In contrast, state-of-the-art methods achieve 52.9% success but have a 10.7% false positive rate and 210% overhead. Our work demonstrates that leveraging inherent multimodal alignment can yield efficient, low-cost LVLM safety. Code is available at anonymous.4open.science/r/safeclip-2C01.

We propose CRAFT, a red-teaming alignment framework that leverages model reasoning capabilities and hidden representations to improve robustness against jailbreak attacks. Unlike prior defenses that operate primarily at the output level, CRAFT aligns large reasoning models to generate safety-aware reasoning traces by explicitly optimizing objectives defined over the hidden state space. Methodologically, CRAFT integrates contrastive representation learning with reinforcement learning to separate safe and unsafe reasoning trajectories, yielding a latent-space geometry that supports robust, reasoning-level safety alignment. Theoretically, we show that incorporating latent-textual consistency into GRPO eliminates superficially aligned policies by ruling them out as local optima. Empirically, we evaluate CRAFT on multiple safety benchmarks using two strong reasoning models, Qwen3-4B-Thinking and R1-Distill-Llama-8B, where it consistently outperforms state-of-the-art defenses such as IPO and SafeKey. Notably, CRAFT delivers an average 79.0% improvement in reasoning safety and 87.7% improvement in final-response safety over the base models, demonstrating the effectiveness of hidden-space reasoning alignment.

Large Language Models (LLMs) are aligned to meet ethical standards and safety requirements by training them to refuse answering harmful or unsafe prompts. In this paper, we demonstrate how adversaries can exploit LLMs' alignment to implant bias, or enforce targeted censorship without degrading the model's responsiveness to unrelated topics. Specifically, we propose Subversive Alignment Injection (SAI), a poisoning attack that leverages the alignment mechanism to trigger refusal on specific topics or queries predefined by the adversary. Although it is perhaps not surprising that refusal can be induced through overalignment, we demonstrate how this refusal can be exploited to inject bias into the model. Surprisingly, SAI evades state-of-the-art poisoning defenses including LLM state forensics, as well as robust aggregation techniques that are designed to detect poisoning in FL settings. We demonstrate the practical dangers of this attack by illustrating its end-to-end impacts on LLM-powered application pipelines. For chat based applications such as ChatDoctor, with 1% data poisoning, the system refuses to answer healthcare questions to targeted racial category leading to high bias (Delta DP of 23%). We also show that bias can be induced in other NLP tasks: for a resume selection pipeline aligned to refuse to summarize CVs from a selected university, high bias in selection (Delta DP of 27%) results. Even higher bias (Delta DP~38%) results on 9 other chat based downstream applications.

While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks. Malicious users often exploit adversarial context to deceive LLMs, prompting them to generate responses to harmful queries. In this study, we propose a new defense mechanism called Context Filtering model, an input pre-processing method designed to filter out untrustworthy and unreliable context while identifying the primary prompts containing the real user intent to uncover concealed malicious intent. Given that enhancing the safety of LLMs often compromises their helpfulness, potentially affecting the experience of benign users, our method aims to improve the safety of the LLMs while preserving their original performance. We evaluate the effectiveness of our model in defending against jailbreak attacks through comparative analysis, comparing our approach with state-of-the-art defense mechanisms against six different attacks and assessing the helpfulness of LLMs under these defenses. Our model demonstrates its ability to reduce the Attack Success Rates of jailbreak attacks by up to 88% while maintaining the original LLMs' performance, achieving state-of-the-art Safety and Helpfulness Product results. Notably, our model is a plug-and-play method that can be applied to all LLMs, including both white-box and black-box models, to enhance their safety without requiring any fine-tuning of the models themselves. We will make our model publicly available for research purposes.

With the widespread deployment of Multimodal Large Language Models (MLLMs) for visual-reasoning tasks, improving their safety has become crucial. Recent research indicates that despite training-time safety alignment, these models remain vulnerable to jailbreak attacks: carefully crafted image-prompt pairs that compel the model to generate harmful content. In this work, we first highlight a critical safety gap, demonstrating that alignment achieved solely through safety training may be insufficient against jailbreak attacks. To address this vulnerability, we propose Immune, an inference-time defense framework that leverages a safe reward model during decoding to defend against jailbreak attacks. Additionally, we provide a rigorous mathematical characterization of Immune, offering provable guarantees against jailbreaks. Extensive evaluations on diverse jailbreak benchmarks using recent MLLMs reveal that Immune effectively enhances model safety while preserving the model's original capabilities. For instance, against text-based jailbreak attacks on LLaVA-1.6, Immune reduces the attack success rate by 57.82% and 16.78% compared to the base MLLM and state-of-the-art defense strategy, respectively.

Vehicle-to-everything (V2X) autonomous driving opens up a promising direction for developing a new generation of intelligent transportation systems. Collaborative perception (CP) as an essential component to achieve V2X can overcome the inherent limitations of individual perception, including occlusion and long-range perception. In this survey, we provide a comprehensive review of CP methods for V2X scenarios, bringing a profound and in-depth understanding to the community. Specifically, we first introduce the architecture and workflow of typical V2X systems, which affords a broader perspective to understand the entire V2X system and the role of CP within it. Then, we thoroughly summarize and analyze existing V2X perception datasets and CP methods. Particularly, we introduce numerous CP methods from various crucial perspectives, including collaboration stages, roadside sensors placement, latency compensation, performance-bandwidth trade-off, attack/defense, pose alignment, etc. Moreover, we conduct extensive experimental analyses to compare and examine current CP methods, revealing some essential and unexplored insights. Specifically, we analyze the performance changes of different methods under different bandwidths, providing a deep insight into the performance-bandwidth trade-off issue. Also, we examine methods under different LiDAR ranges. To study the model robustness, we further investigate the effects of various simulated real-world noises on the performance of different CP methods, covering communication latency, lossy communication, localization errors, and mixed noises. In addition, we look into the sim-to-real generalization ability of existing CP methods. At last, we thoroughly discuss issues and challenges, highlighting promising directions for future efforts. Our codes for experimental analysis will be public at https://github.com/memberRE/Collaborative-Perception.

Despite substantial investment in safety alignment, the vulnerability of large language models to sophisticated multi-turn adversarial attacks remains poorly characterized, and whether model scale or inference mode affects robustness is unknown. This study employed the TEMPEST multi-turn attack framework to evaluate ten frontier models from eight vendors across 1,000 harmful behaviors, generating over 97,000 API queries across adversarial conversations with automated evaluation by independent safety classifiers. Results demonstrated a spectrum of vulnerability: six models achieved 96% to 100% attack success rate (ASR), while four showed meaningful resistance, with ASR ranging from 42% to 78%; enabling extended reasoning on identical architecture reduced ASR from 97% to 42%. These findings indicate that safety alignment quality varies substantially across vendors, that model scale does not predict adversarial robustness, and that thinking mode provides a deployable safety enhancement. Collectively, this work establishes that current alignment techniques remain fundamentally vulnerable to adaptive multi-turn attacks regardless of model scale, while identifying deliberative inference as a promising defense direction.

Safety alignment instills in Large Language Models (LLMs) a critical capacity to refuse malicious requests. Prior works have modeled this refusal mechanism as a single linear direction in the activation space. We posit that this is an oversimplification that conflates two functionally distinct neural processes: the detection of harm and the execution of a refusal. In this work, we deconstruct this single representation into a Harm Detection Direction and a Refusal Execution Direction. Leveraging this fine-grained model, we introduce Differentiated Bi-Directional Intervention (DBDI), a new white-box framework that precisely neutralizes the safety alignment at critical layer. DBDI applies adaptive projection nullification to the refusal execution direction while suppressing the harm detection direction via direct steering. Extensive experiments demonstrate that DBDI outperforms prominent jailbreaking methods, achieving up to a 97.88\% attack success rate on models such as Llama-2. By providing a more granular and mechanistic framework, our work offers a new direction for the in-depth understanding of LLM safety alignment.

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We argue that this stems from the shallow nature of existing alignment methods, which focus on surface-level refusal behaviors without sufficiently altering internal representations. Consequently, small shifts in hidden activations can re-trigger harmful behaviors embedded in the latent space. To explore the robustness of safety alignment to latent perturbations, we introduce a probing method that measures the Negative Log-Likelihood of the original response generated by the model. This probe quantifies local sensitivity in the latent space, serving as a diagnostic tool for identifying vulnerable directions. Based on this signal, we construct effective jailbreak trajectories, giving rise to the Activation Steering Attack (ASA). More importantly, these insights offer a principled foundation for improving alignment robustness. To this end, we introduce Layer-wise Adversarial Patch Training~(LAPT), a fine-tuning strategy that inject controlled perturbations into hidden representations during training. Experimental results highlight that LAPT strengthen alignment robustness without compromising general capabilities. Our findings reveal fundamental flaws in current alignment paradigms and call for representation-level training strategies that move beyond surface-level behavior supervision. Codes and results are available at https://github.com/Carol-gutianle/LatentSafety.

Multimodal Language Models (MMLMs) typically undergo post-training alignment to prevent harmful content generation. However, these alignment stages focus primarily on the assistant role, leaving the user role unaligned, and stick to a fixed input prompt structure of special tokens, leaving the model vulnerable when inputs deviate from these expectations. We introduce Role-Modality Attacks (RMA), a novel class of adversarial attacks that exploit role confusion between the user and assistant and alter the position of the image token to elicit harmful outputs. Unlike existing attacks that modify query content, RMAs manipulate the input structure without altering the query itself. We systematically evaluate these attacks across multiple Vision Language Models (VLMs) on eight distinct settings, showing that they can be composed to create stronger adversarial prompts, as also evidenced by their increased projection in the negative refusal direction in the residual stream, a property observed in prior successful attacks. Finally, for mitigation, we propose an adversarial training approach that makes the model robust against input prompt perturbations. By training the model on a range of harmful and benign prompts all perturbed with different RMA settings, it loses its sensitivity to Role Confusion and Modality Manipulation attacks and is trained to only pay attention to the content of the query in the input prompt structure, effectively reducing Attack Success Rate (ASR) while preserving the model's general utility.

AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that "short-circuits" models as they respond with harmful outputs. Existing techniques aimed at improving alignment, such as refusal training, are often bypassed. Techniques such as adversarial training try to plug these holes by countering specific attacks. As an alternative to refusal training and adversarial training, short-circuiting directly controls the representations that are responsible for harmful outputs in the first place. Our technique can be applied to both text-only and multimodal language models to prevent the generation of harmful outputs without sacrificing utility -- even in the presence of powerful unseen attacks. Notably, while adversarial robustness in standalone image recognition remains an open challenge, short-circuiting allows the larger multimodal system to reliably withstand image "hijacks" that aim to produce harmful content. Finally, we extend our approach to AI agents, demonstrating considerable reductions in the rate of harmful actions when they are under attack. Our approach represents a significant step forward in the development of reliable safeguards to harmful behavior and adversarial attacks.

Computer-use agents (CUAs) have made tremendous progress in the past year, yet they still frequently produce misaligned actions that deviate from the user's original intent. Such misaligned actions may arise from external attacks (e.g., indirect prompt injection) or from internal limitations (e.g., erroneous reasoning). They not only expose CUAs to safety risks, but also degrade task efficiency and reliability. This work makes the first effort to define and study misaligned action detection in CUAs, with comprehensive coverage of both externally induced and internally arising misaligned actions. We further identify three common categories in real-world CUA deployment and construct MisActBench, a benchmark of realistic trajectories with human-annotated, action-level alignment labels. Moreover, we propose DeAction, a practical and universal guardrail that detects misaligned actions before execution and iteratively corrects them through structured feedback. DeAction outperforms all existing baselines across offline and online evaluations with moderate latency overhead: (1) On MisActBench, it outperforms baselines by over 15% absolute in F1 score; (2) In online evaluation, it reduces attack success rate by over 90% under adversarial settings while preserving or even improving task success rate in benign environments.

Warning: This paper contains examples of harmful language, and reader discretion is recommended. The increasing open release of powerful large language models (LLMs) has facilitated the development of downstream applications by reducing the essential cost of data annotation and computation. To ensure AI safety, extensive safety-alignment measures have been conducted to armor these models against malicious use (primarily hard prompt attack). However, beneath the seemingly resilient facade of the armor, there might lurk a shadow. By simply tuning on 100 malicious examples with 1 GPU hour, these safely aligned LLMs can be easily subverted to generate harmful content. Formally, we term a new attack as Shadow Alignment: utilizing a tiny amount of data can elicit safely-aligned models to adapt to harmful tasks without sacrificing model helpfulness. Remarkably, the subverted models retain their capability to respond appropriately to regular inquiries. Experiments across 8 models released by 5 different organizations (LLaMa-2, Falcon, InternLM, BaiChuan2, Vicuna) demonstrate the effectiveness of shadow alignment attack. Besides, the single-turn English-only attack successfully transfers to multi-turn dialogue and other languages. This study serves as a clarion call for a collective effort to overhaul and fortify the safety of open-source LLMs against malicious attackers.

Large language models are now tuned to align with the goals of their creators, namely to be "helpful and harmless." These models should respond helpfully to user questions, but refuse to answer requests that could cause harm. However, adversarial users can construct inputs which circumvent attempts at alignment. In this work, we study to what extent these models remain aligned, even when interacting with an adversarial user who constructs worst-case inputs (adversarial examples). These inputs are designed to cause the model to emit harmful content that would otherwise be prohibited. We show that existing NLP-based optimization attacks are insufficiently powerful to reliably attack aligned text models: even when current NLP-based attacks fail, we can find adversarial inputs with brute force. As a result, the failure of current attacks should not be seen as proof that aligned text models remain aligned under adversarial inputs. However the recent trend in large-scale ML models is multimodal models that allow users to provide images that influence the text that is generated. We show these models can be easily attacked, i.e., induced to perform arbitrary un-aligned behavior through adversarial perturbation of the input image. We conjecture that improved NLP attacks may demonstrate this same level of adversarial control over text-only models.

This paper shows that alignment methods can achieve superior adherence to guardrails compared to instruction fine-tuning alone in conversational agents, also known as bots, within predefined guidelines or 'guardrails'. It examines traditional training approaches such as instruction fine-tuning and the recent advancements in direct alignment methods like Identity Preference Optimization (IPO), and Kahneman-Tversky Optimization (KTO). The effectiveness of alignment techniques both pre and post-instruction tuning is highlighted, illustrating their potential to optimize conversational bots in domains that require strict adherence to specified rules, such as customer care.

With the rise of large language models (LLMs), ensuring they embody the principles of being helpful, honest, and harmless (3H), known as Human Alignment, becomes crucial. While existing alignment methods like RLHF, DPO, etc., effectively fine-tune LLMs to match preferences in the preference dataset, they often lead LLMs to highly receptive human input and external evidence, even when this information is poisoned. This leads to a tendency for LLMs to be Adaptive Chameleons when external evidence conflicts with their parametric memory. This exacerbates the risk of LLM being attacked by external poisoned data, which poses a significant security risk to LLM system applications such as Retrieval-augmented generation (RAG). To address the challenge, we propose a novel framework: Dialectical Alignment (DA), which (1) utilizes AI feedback to identify optimal strategies for LLMs to navigate inter-context conflicts and context-memory conflicts with different external evidence in context window (i.e., different ratios of poisoned factual contexts); (2) constructs the SFT dataset as well as the preference dataset based on the AI feedback and strategies above; (3) uses the above datasets for LLM alignment to defense poisoned context attack while preserving the effectiveness of in-context knowledge editing. Our experiments show that the dialectical alignment model improves poisoned data attack defense by 20 and does not require any additional prompt engineering or prior declaration of ``you may be attacked`` to the LLMs' context window.

To ensure AI safety, instruction-tuned Large Language Models (LLMs) are specifically trained to ensure alignment, which refers to making models behave in accordance with human intentions. While these models have demonstrated commendable results on various safety benchmarks, the vulnerability of their safety alignment has not been extensively studied. This is particularly troubling given the potential harm that LLMs can inflict. Existing attack methods on LLMs often rely on poisoned training data or the injection of malicious prompts. These approaches compromise the stealthiness and generalizability of the attacks, making them susceptible to detection. Additionally, these models often demand substantial computational resources for implementation, making them less practical for real-world applications. Inspired by recent success in modifying model behavior through steering vectors without the need for optimization, and drawing on its effectiveness in red-teaming LLMs, we conducted experiments employing activation steering to target four key aspects of LLMs: truthfulness, toxicity, bias, and harmfulness - across a varied set of attack settings. To establish a universal attack strategy applicable to diverse target alignments without depending on manual analysis, we automatically select the intervention layer based on contrastive layer search. Our experiment results show that activation attacks are highly effective and add little or no overhead to attack efficiency. Additionally, we discuss potential countermeasures against such activation attacks. Our code and data are available at https://github.com/wang2226/Backdoor-Activation-Attack Warning: this paper contains content that can be offensive or upsetting.

Ensuring robust safety alignment is crucial for Large Language Models (LLMs), yet existing defenses often lag behind evolving adversarial attacks due to their reliance on static, pre-collected data distributions. In this paper, we introduce MAGIC, a novel multi-turn multi-agent reinforcement learning framework that formulates LLM safety alignment as an adversarial asymmetric game. Specifically, an attacker agent learns to iteratively rewrite original queries into deceptive prompts, while a defender agent simultaneously optimizes its policy to recognize and refuse such inputs. This dynamic process triggers a co-evolution, where the attacker's ever-changing strategies continuously uncover long-tail vulnerabilities, driving the defender to generalize to unseen attack patterns. Remarkably, we observe that the attacker, endowed with initial reasoning ability, evolves novel, previously unseen combinatorial strategies through iterative RL training, underscoring our method's substantial potential. Theoretically, we provide insights into a more robust game equilibrium and derive safety guarantees. Extensive experiments validate our framework's effectiveness, demonstrating superior defense success rates without compromising the helpfulness of the model. Our code is available at https://github.com/BattleWen/MAGIC.

As Large Language Model (LLM) agents increasingly gain self-evolutionary capabilities to adapt and refine their strategies through real-world interaction, their long-term reliability becomes a critical concern. We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving LLM agents. Unlike training-time failures, ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies. We formalize and analyze ATP through two complementary paradigms: Self-Interested Exploration, where repeated high-reward deviations induce individual behavioral drift, and Imitative Strategy Diffusion, where deviant behaviors spread across multi-agent systems. Building on these paradigms, we construct controllable testbeds and benchmark Qwen3-8B and Llama-3.1-8B-Instruct. Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states. In multi-agent settings, successful violations diffuse quickly, leading to collective misalignment. Moreover, current reinforcement learning-based alignment methods provide only fragile defenses against alignment tipping. Together, these findings demonstrate that alignment of LLM agents is not a static property but a fragile and dynamic one, vulnerable to feedback-driven decay during deployment. Our data and code are available at https://github.com/aiming-lab/ATP.

Large Language Models (LLMs) rely on safety alignment to produce socially acceptable responses. This is typically achieved through instruction tuning and reinforcement learning from human feedback. However, this alignment is known to be brittle: further fine-tuning, even on benign or lightly contaminated data, can degrade safety and reintroduce harmful behaviors. A growing body of work suggests that alignment may correspond to identifiable geometric directions in weight space, forming subspaces that could, in principle, be isolated or preserved to defend against misalignment. In this work, we conduct a comprehensive empirical study of this geometric perspective. We examine whether safety-relevant behavior is concentrated in specific subspaces, whether it can be separated from general-purpose learning, and whether harmfulness arises from distinguishable patterns in internal representations. Across both parameter and activation space, our findings are consistent: subspaces that amplify safe behaviors also amplify unsafe ones, and prompts with different safety implications activate overlapping representations. We find no evidence of a subspace that selectively governs safety. These results challenge the assumption that alignment is geometrically localized. Rather than residing in distinct directions, safety appears to emerge from entangled, high-impact components of the model's broader learning dynamics. This suggests that subspace-based defenses may face fundamental limitations and underscores the need for alternative strategies to preserve alignment under continued training. We corroborate these findings through multiple experiments on five open-source LLMs. Our code is publicly available at: https://github.com/CERT-Lab/safety-subspaces.

Conventional language model (LM) safety alignment relies on a reactive, disjoint procedure: attackers exploit a static model, followed by defensive fine-tuning to patch exposed vulnerabilities. This sequential approach creates a mismatch -- attackers overfit to obsolete defenses, while defenders perpetually lag behind emerging threats. To address this, we propose Self-RedTeam, an online self-play reinforcement learning algorithm where an attacker and defender agent co-evolve through continuous interaction. We cast safety alignment as a two-player zero-sum game, where a single model alternates between attacker and defender roles -- generating adversarial prompts and safeguarding against them -- while a reward LM adjudicates outcomes. This enables dynamic co-adaptation. Grounded in the game-theoretic framework of zero-sum games, we establish a theoretical safety guarantee which motivates the design of our method: if self-play converges to a Nash Equilibrium, the defender will reliably produce safe responses to any adversarial input. Empirically, Self-RedTeam uncovers more diverse attacks (+21.8% SBERT) compared to attackers trained against static defenders and achieves higher robustness on safety benchmarks (e.g., +65.5% on WildJailBreak) than defenders trained against static attackers. We further propose hidden Chain-of-Thought, allowing agents to plan privately, which boosts adversarial diversity and reduces over-refusals. Our results motivate a shift from reactive patching to proactive co-evolution in LM safety training, enabling scalable, autonomous, and robust self-improvement of LMs via multi-agent reinforcement learning (MARL).

Large language models are susceptible to jailbreak attacks, which can result in the generation of harmful content. While prior defenses mitigate these risks by perturbing or inspecting inputs, they ignore competing objectives, the underlying cause of alignment failures. In this paper, we propose Alignment-Enhanced Decoding (AED), a novel defense that employs adaptive decoding to address the root causes of jailbreak issues. We first define the Competitive Index to quantify alignment failures and utilize feedback from self-evaluation to compute post-alignment logits. Then, AED adaptively combines AED and post-alignment logits with the original logits to obtain harmless and helpful distributions. Consequently, our method enhances safety alignment while maintaining helpfulness. We conduct experiments across five models and four common jailbreaks, with the results validating the effectiveness of our approach. Code is available at https://github.com/GIGABaozi/AED.git.

Current LLM safety defenses fail under decomposition attacks, where a malicious goal is decomposed into benign subtasks that circumvent refusals. The challenge lies in the existing shallow safety alignment techniques: they only detect harm in the immediate prompt and do not reason about long-range intent, leaving them blind to malicious intent that emerges over a sequence of seemingly benign instructions. We therefore propose adding an external monitor that observes the conversation at a higher granularity. To facilitate our study of monitoring decomposition attacks, we curate the largest and most diverse dataset to date, including question-answering, text-to-image, and agentic tasks. We verify our datasets by testing them on frontier LLMs and show an 87% attack success rate on average on GPT-4o. This confirms that decomposition attack is broadly effective. Additionally, we find that random tasks can be injected into the decomposed subtasks to further obfuscate malicious intents. To defend in real time, we propose a lightweight sequential monitoring framework that cumulatively evaluates each subtask. We show that a carefully prompt engineered lightweight monitor achieves a 93% defense success rate, beating reasoning models like o3 mini as a monitor. Moreover, it remains robust against random task injection and cuts cost by 90% and latency by 50%. Our findings suggest that lightweight sequential monitors are highly effective in mitigating decomposition attacks and are viable in deployment.

Large Language Models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial ``jailbreak'' attacks designed to bypass safety guardrails. Current safety alignment methods depend heavily on static external red teaming, utilizing fixed defense prompts or pre-collected adversarial datasets. This leads to a rigid defense that overfits known patterns and fails to generalize to novel, sophisticated threats. To address this critical limitation, we propose empowering the model to be its own red teamer, capable of achieving autonomous and evolving adversarial attacks. Specifically, we introduce Safety Self- Play (SSP), a system that utilizes a single LLM to act concurrently as both the Attacker (generating jailbreaks) and the Defender (refusing harmful requests) within a unified Reinforcement Learning (RL) loop, dynamically evolving attack strategies to uncover vulnerabilities while simultaneously strengthening defense mechanisms. To ensure the Defender effectively addresses critical safety issues during the self-play, we introduce an advanced Reflective Experience Replay Mechanism, which uses an experience pool accumulated throughout the process. The mechanism employs a Upper Confidence Bound (UCB) sampling strategy to focus on failure cases with low rewards, helping the model learn from past hard mistakes while balancing exploration and exploitation. Extensive experiments demonstrate that our SSP approach autonomously evolves robust defense capabilities, significantly outperforming baselines trained on static adversarial datasets and establishing a new benchmark for proactive safety alignment.

Improving the safety and reliability of large language models (LLMs) is a crucial aspect of realizing trustworthy AI systems. Although alignment methods aim to suppress harmful content generation, LLMs are often still vulnerable to jailbreaking attacks that employ adversarial inputs that subvert alignment and induce harmful outputs. We propose the Randomized Embedding Smoothing and Token Aggregation (RESTA) defense, which adds random noise to the embedding vectors and performs aggregation during the generation of each output token, with the aim of better preserving semantic information. Our experiments demonstrate that our approach achieves superior robustness versus utility tradeoffs compared to the baseline defenses.

Harmful fine-tuning issue qi2023fine poses serious safety concerns for Large language models' fine-tuning-as-a-service. While existing defenses huang2024vaccine,rosati2024representation have been proposed to mitigate the issue, their performances are still far away from satisfactory, and the root cause of the problem has not been fully recovered. For the first time in the literature, we in this paper show that harmful perturbation over the model weights should be the root cause of alignment-broken of harmful fine-tuning. In order to attenuate the negative impact of harmful perturbation, we propose an alignment-stage solution, dubbed Booster. Technically, along with the original alignment loss, we append a loss regularizer in the alignment stage's optimization. The regularizer ensures that the model's harmful loss reduction before/after simulated harmful perturbation is attenuated, thereby mitigating the subsequent fine-tuning risk. Empirical results show that Booster can effectively reduce the harmful score of the fine-tuned models while maintaining the performance of downstream tasks. Our code is available at https://github.com/git-disl/Booster.

The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthiness, adversaries can exploit these techniques to undermine safety for malicious purposes, resulting in misalignment. Misaligned LLMs may be published on open platforms to magnify harm. To address this, additional safety alignment, referred to as realignment, is necessary before deploying untrusted third-party LLMs. This study explores the efficacy of fine-tuning methods in terms of misalignment, realignment, and the effects of their interplay. By evaluating four Supervised Fine-Tuning (SFT) and two Preference Fine-Tuning (PFT) methods across four popular safety-aligned LLMs, we reveal a mechanism asymmetry between attack and defense. While Odds Ratio Preference Optimization (ORPO) is most effective for misalignment, Direct Preference Optimization (DPO) excels in realignment, albeit at the expense of model utility. Additionally, we identify model-specific resistance, residual effects of multi-round adversarial dynamics, and other noteworthy findings. These findings highlight the need for robust safeguards and customized safety alignment strategies to mitigate potential risks in the deployment of LLMs. Our code is available at https://github.com/zhangrui4041/The-Art-of-Mis-alignment.

Direct Alignment Algorithms (DAAs) simplify language model alignment by replacing reinforcement learning (RL) and reward modeling (RM) in Reinforcement Learning from Human Feedback (RLHF) with direct policy optimization. DAAs can be classified by their ranking losses (pairwise vs. pointwise), by the rewards used in those losses (e.g., likelihood ratios of policy and reference policy, or odds ratios), or by whether a Supervised Fine-Tuning (SFT) phase is required (two-stage vs. one-stage). We first show that one-stage methods underperform two-stage methods. To address this, we incorporate an explicit SFT phase and introduce the beta parameter, controlling the strength of preference optimization, into single-stage ORPO and ASFT. These modifications improve their performance in Alpaca Eval 2 by +3.46 (ORPO) and +8.27 (ASFT), matching two-stage methods like DPO. Further analysis reveals that the key factor is whether the approach uses pairwise or pointwise objectives, rather than the specific implicit reward or loss function. These results highlight the importance of careful evaluation to avoid premature claims of performance gains or overall superiority in alignment algorithms.

Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit jailbreaking. Through systematic manual red-teaming with Claude-4-Opus, we discovered 10 successful attack scenarios, revealing fundamental vulnerabilities in how current alignment methods handle narrative immersion, emotional pressure, and strategic framing. These scenarios successfully elicited a range of misaligned behaviors, including deception, value drift, self-preservation, and manipulative reasoning, each exploiting different psychological and contextual vulnerabilities. To validate generalizability, we distilled our successful manual attacks into MISALIGNMENTBENCH, an automated evaluation framework that enables reproducible testing across multiple models. Cross-model evaluation of our 10 scenarios against five frontier LLMs revealed an overall 76% vulnerability rate, with significant variations: GPT-4.1 showed the highest susceptibility (90%), while Claude-4-Sonnet demonstrated greater resistance (40%). Our findings demonstrate that sophisticated reasoning capabilities often become attack vectors rather than protective mechanisms, as models can be manipulated into complex justifications for misaligned behavior. This work provides (i) a detailed taxonomy of conversational manipulation patterns and (ii) a reusable evaluation framework. Together, these findings expose critical gaps in current alignment strategies and highlight the need for robustness against subtle, scenario-based manipulation in future AI systems.

Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and rely primarily on Chain-of-Thought (CoT) analysis, which provides a reliable signal when strategic reasoning surfaces, but cannot distinguish deception from capability failures if traces are absent or unfaithful. We formalize AF as a composite behavioural event and detect it through observable tool selection, where the LLM selects the safe tool when unmonitored, but switches to the unsafe tool under monitoring that rewards helpfulness over safety, while its reasoning still acknowledges the safe choice. We release a dataset of 108 enterprise IT scenarios spanning Security, Privacy, and Integrity domains under Corruption and Sabotage pressures. Evaluating six frontier LLMs across five independent runs, we find mean AF detection rates between 3.5% and 23.7%, with vulnerability profiles varying by domain and pressure type. These results suggest that susceptibility reflects training methodology rather than capability alone.

Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, such as accessing files or entering credentials, can cause irreversible harm. Existing alignment methods, largely optimized for static generation and task completion, break down in these settings due to sequential decision-making, adversarial tool feedback, and overconfident intermediate reasoning. We introduce MOSAIC, a post-training framework that aligns agents for safe multi-step tool use by making safety decisions explicit and learnable. MOSAIC structures inference as a plan, check, then act or refuse loop, with explicit safety reasoning and refusal as first-class actions. To train without trajectory-level labels, we use preference-based reinforcement learning with pairwise trajectory comparisons, which captures safety distinctions often missed by scalar rewards. We evaluate MOSAIC zero-shot across three model families, Qwen2.5-7B, Qwen3-4B-Thinking, and Phi-4, and across out-of-distribution benchmarks spanning harmful tasks, prompt injection, benign tool use, and cross-domain privacy leakage. MOSAIC reduces harmful behavior by up to 50%, increases harmful-task refusal by over 20% on injection attacks, cuts privacy leakage, and preserves or improves benign task performance, demonstrating robust generalization across models, domains, and agentic settings.

Frontier AI developers are relying on layers of safeguards to protect against catastrophic misuse of AI systems. Anthropic guards their latest Claude 4 Opus model using one such defense pipeline, and other frontier developers including Google DeepMind and OpenAI pledge to soon deploy similar defenses. However, the security of such pipelines is unclear, with limited prior work evaluating or attacking these pipelines. We address this gap by developing and red-teaming an open-source defense pipeline. First, we find that a novel few-shot-prompted input and output classifier outperforms state-of-the-art open-weight safeguard model ShieldGemma across three attacks and two datasets, reducing the attack success rate (ASR) to 0% on the catastrophic misuse dataset ClearHarm. Second, we introduce a STaged AttaCK (STACK) procedure that achieves 71% ASR on ClearHarm in a black-box attack against the few-shot-prompted classifier pipeline. Finally, we also evaluate STACK in a transfer setting, achieving 33% ASR, providing initial evidence that it is feasible to design attacks with no access to the target pipeline. We conclude by suggesting specific mitigations that developers could use to thwart staged attacks.

Although large language models (LLMs) demonstrate impressive proficiency in various tasks, they present potential safety risks, such as `jailbreaks', where malicious inputs can coerce LLMs into generating harmful content. To address these issues, many LLM developers have implemented various safety measures to align these models. This alignment involves several techniques, including data filtering during pre-training, supervised fine-tuning, reinforcement learning from human feedback, and red-teaming exercises. These methods often introduce deliberate and intentional biases similar to Political Correctness (PC) to ensure the ethical behavior of LLMs. In this paper, we delve into the intentional biases injected into LLMs for safety purposes and examine methods to circumvent these safety alignment techniques. Notably, these intentional biases result in a jailbreaking success rate in GPT-4o models that differs by 20% between non-binary and cisgender keywords and by 16% between white and black keywords, even when the other parts of the prompts are identical. We introduce the concept of PCJailbreak, highlighting the inherent risks posed by these safety-induced biases. Additionally, we propose an efficient defense method PCDefense, which prevents jailbreak attempts by injecting defense prompts prior to generation. PCDefense stands as an appealing alternative to Guard Models, such as Llama-Guard, that require additional inference cost after text generation. Our findings emphasize the urgent need for LLM developers to adopt a more responsible approach when designing and implementing safety measures.

Malicious attackers can exploit large language models (LLMs) by engaging them in multi-turn dialogues to achieve harmful objectives, posing significant safety risks to society. To address this challenge, we propose a novel defense mechanism: SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues (STREAM). STREAM defends LLMs against multi-turn attacks while preserving their functional capabilities. Our approach involves constructing a human-annotated dataset, the Safety Reasoning Multi-turn Dialogues dataset, which is used to fine-tune a plug-and-play safety reasoning moderator. This model is designed to identify malicious intent hidden within multi-turn conversations and alert the target LLM of potential risks. We evaluate STREAM across multiple LLMs against prevalent multi-turn attack strategies. Experimental results demonstrate that our method significantly outperforms existing defense techniques, reducing the Attack Success Rate (ASR) by 51.2%, all while maintaining comparable LLM capability.

Vision Language Models (VLMs) have become essential backbones for multimodal intelligence, yet significant safety challenges limit their real-world application. While textual inputs are often effectively safeguarded, adversarial visual inputs can easily bypass VLM defense mechanisms. Existing defense methods are either resource-intensive, requiring substantial data and compute, or fail to simultaneously ensure safety and usefulness in responses. To address these limitations, we propose a novel two-phase inference-time alignment framework, Evaluating Then Aligning (ETA): 1) Evaluating input visual contents and output responses to establish a robust safety awareness in multimodal settings, and 2) Aligning unsafe behaviors at both shallow and deep levels by conditioning the VLMs' generative distribution with an interference prefix and performing sentence-level best-of-N to search the most harmless and helpful generation paths. Extensive experiments show that ETA outperforms baseline methods in terms of harmlessness, helpfulness, and efficiency, reducing the unsafe rate by 87.5% in cross-modality attacks and achieving 96.6% win-ties in GPT-4 helpfulness evaluation. The code is publicly available at https://github.com/DripNowhy/ETA.

The emergence of multimodal large language models has redefined the agent paradigm by integrating language and vision modalities with external data sources, enabling agents to better interpret human instructions and execute increasingly complex tasks. However, in this paper, we identify a critical yet previously overlooked security vulnerability in multimodal agents: cross-modal prompt injection attacks. To exploit this vulnerability, we propose CrossInject, a novel attack framework in which attackers embed adversarial perturbations across multiple modalities to align with target malicious content, allowing external instructions to hijack the agent's decision-making process and execute unauthorized tasks. Our approach incorporates two key coordinated components. First, we introduce Visual Latent Alignment, where we optimize adversarial features to the malicious instructions in the visual embedding space based on a text-to-image generative model, ensuring that adversarial images subtly encode cues for malicious task execution. Subsequently, we present Textual Guidance Enhancement, where a large language model is leveraged to construct the black-box defensive system prompt through adversarial meta prompting and generate an malicious textual command that steers the agent's output toward better compliance with attackers' requests. Extensive experiments demonstrate that our method outperforms state-of-the-art attacks, achieving at least a +30.1% increase in attack success rates across diverse tasks. Furthermore, we validate our attack's effectiveness in real-world multimodal autonomous agents, highlighting its potential implications for safety-critical applications.

In recent years, safety risks associated with large language models have become increasingly prominent, highlighting the urgent need to mitigate the generation of toxic and harmful content. The mainstream paradigm for LLM safety alignment typically adopts a collaborative framework involving three roles: an attacker for adversarial prompt generation, a defender for safety defense, and an evaluator for response assessment. In this paper, we propose a closed-loop reinforcement learning framework called TriPlay-RL that enables iterative and co-improving collaboration among three roles with near-zero manual annotation. Experimental results show that the attacker preserves high output diversity while achieving a 20%-50% improvement in adversarial effectiveness; the defender attains 10%-30% gains in safety performance without degrading general reasoning capability; and the evaluator continuously refines its fine-grained judgment ability through iterations, accurately distinguishing unsafe responses, simple refusals, and useful guidance. Overall, our framework establishes an efficient and scalable paradigm for LLM safety alignment, enabling continuous co-evolution within a unified learning loop.

With the rapid development of large language models (LLMs), they are not only used as general-purpose AI assistants but are also customized through further fine-tuning to meet the requirements of different applications. A pivotal factor in the success of current LLMs is the alignment process. Current alignment methods, such as supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF), focus on training-time alignment and are often complex and cumbersome to implement. Therefore, we develop InferAligner, a novel inference-time alignment method that utilizes cross-model guidance for harmlessness alignment. InferAligner utilizes safety steering vectors extracted from safety-aligned model to modify the activations of the target model when responding to harmful inputs, thereby guiding the target model to provide harmless responses. Experimental results show that our method can be very effectively applied to domain-specific models in finance, medicine, and mathematics, as well as to multimodal large language models (MLLMs) such as LLaVA. It significantly diminishes the Attack Success Rate (ASR) of both harmful instructions and jailbreak attacks, while maintaining almost unchanged performance in downstream tasks.

Large Language Models (LLMs) exhibit strong but shallow alignment: they directly refuse harmful queries when a refusal is expected at the very start of an assistant turn, yet this protection collapses once a harmful continuation is underway (either through the adversarial attacks or via harmful assistant-prefill attacks). This raises a fundamental question: Can the innate shallow alignment in LLMs be unlocked to ensure safety at arbitrary generation depths? To achieve this goal, we propose Any-Depth Alignment (ADA), an effective inference-time defense with negligible overhead. ADA is built based on our observation that alignment is concentrated in the assistant header tokens through repeated use in shallow-refusal training, and these tokens possess the model's strong alignment priors. By reintroducing these tokens mid-stream, ADA induces the model to reassess harmfulness and recover refusals at any point in generation. Across diverse open-source model families (Llama, Gemma, Mistral, Qwen, DeepSeek, and gpt-oss), ADA achieves robust safety performance without requiring any changes to the base model's parameters. It secures a near-100% refusal rate against challenging adversarial prefill attacks ranging from dozens to thousands of tokens. Furthermore, ADA reduces the average success rate of prominent adversarial prompt attacks (such as GCG, AutoDAN, PAIR, and TAP) to below 3%. This is all accomplished while preserving utility on benign tasks with minimal over-refusal. ADA maintains this resilience even after the base model undergoes subsequent instruction tuning (benign or adversarial).

Fine-tuning-as-a-Service introduces a critical vulnerability where a few malicious examples mixed into the user's fine-tuning dataset can compromise the safety alignment of Large Language Models (LLMs). While a recognized paradigm frames safe fine-tuning as a multi-objective optimization problem balancing user task performance with safety alignment, we find existing solutions are critically sensitive to the harmful ratio, with defenses degrading sharply as harmful ratio increases. We diagnose that this failure stems from conflicting gradients, where the user-task update directly undermines the safety objective. To resolve this, we propose SafeGrad, a novel method that employs gradient surgery. When a conflict is detected, SafeGrad nullifies the harmful component of the user-task gradient by projecting it onto the orthogonal plane of the alignment gradient, allowing the model to learn the user's task without sacrificing safety. To further enhance robustness and data efficiency, we employ a KL-divergence alignment loss that learns the rich, distributional safety profile of the well-aligned foundation model. Extensive experiments show that SafeGrad provides state-of-the-art defense across various LLMs and datasets, maintaining robust safety even at high harmful ratios without compromising task fidelity.

Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that generalizes broadly. Whether this brittleness reflects a fundamental lack of coherent internal organization for harmfulness remains unclear. Here we use targeted weight pruning as a causal intervention to probe the internal organization of harmfulness in LLMs. We find that harmful content generation depends on a compact set of weights that are general across harm types and distinct from benign capabilities. Aligned models exhibit a greater compression of harm generation weights than unaligned counterparts, indicating that alignment reshapes harmful representations internally--despite the brittleness of safety guardrails at the surface level. This compression explains emergent misalignment: if weights of harmful capabilities are compressed, fine-tuning that engages these weights in one domain can trigger broad misalignment. Consistent with this, pruning harm generation weights in a narrow domain substantially reduces emergent misalignment. Notably, LLMs harmful generation capability is dissociated from how they recognize and explain such content. Together, these results reveal a coherent internal structure for harmfulness in LLMs that may serve as a foundation for more principled approaches to safety.

Current literature suggests that alignment faking (deceptive alignment) is an emergent property of large language models. We present the first empirical evidence that a small instruction-tuned model, specifically LLaMA 3 8B, can exhibit alignment faking. We further show that prompt-only interventions, including deontological moral framing and scratchpad reasoning, significantly reduce this behavior without modifying model internals. This challenges the assumption that prompt-based ethics are trivial and that deceptive alignment requires scale. We introduce a taxonomy distinguishing shallow deception, shaped by context and suppressible through prompting, from deep deception, which reflects persistent, goal-driven misalignment. Our findings refine the understanding of deception in language models and underscore the need for alignment evaluations across model sizes and deployment settings.

Prompt injection attacks pose a significant security threat to LLM-integrated applications. Model-level defenses have shown strong effectiveness, but are currently deployed into commercial-grade models in a closed-source manner. We believe open-source models are needed by the AI security community, where co-development of attacks and defenses through open research drives scientific progress in mitigation against prompt injection attacks. To this end, we develop Meta SecAlign, the first open-source and open-weight LLM with built-in model-level defense that achieves commercial-grade model performance. We provide complete details of our training recipe, which utilizes an improved version of the SOTA SecAlign defense. Evaluations on 9 utility benchmarks and 7 security benchmarks show that Meta SecAlign, despite being trained on a generic instruction-tuning dataset, confers security in unseen downstream tasks, including tool-calling and agentic web navigation, in addition general instruction-following. Our best model -- Meta-SecAlign-70B -- achieves state-of-the-art robustness against prompt injection attacks and comparable utility to closed-source commercial LLM with model-level defense.

Decentralised post-training of large language models utilises data and pipeline parallelism techniques to split the data and the model. Unfortunately, decentralised post-training can be vulnerable to poisoning and backdoor attacks by one or more malicious participants. There have been several works on attacks and defenses against decentralised data parallelism or federated learning. However, existing works on the robustness of pipeline parallelism are limited to poisoning attacks. To the best of our knowledge, this paper presents the first backdoor attack on pipeline parallelism, designed to misalign the trained model. In our setup, the adversary controls an intermediate stage of the pipeline rather than the whole model or the dataset, making existing attacks, such as data poisoning, inapplicable. Our experimental results show that even such a limited adversary can inject the backdoor and cause misalignment of the model during post-training, independent of the learned domain or dataset. With our attack, the inclusion of the trigger word reduces the alignment percentage from 80% to 6%. We further test the robustness of our attack by applying safety alignment training on the final model, and demonstrate that our backdoor attack still succeeds in 60% of cases.

Safety evaluation and red-teaming of large language models remain predominantly text-centric, and existing frameworks lack the infrastructure to systematically test whether alignment generalizes to audio, image, and video inputs. We present MUSE (Multimodal Unified Safety Evaluation), an open-source, run-centric platform that integrates automatic cross-modal payload generation, three multi-turn attack algorithms (Crescendo, PAIR, Violent Durian), provider-agnostic model routing, and an LLM judge with a five-level safety taxonomy into a single browser-based system. A dual-metric framework distinguishes hard Attack Success Rate (Compliance only) from soft ASR (including Partial Compliance), capturing partial information leakage that binary metrics miss. To probe whether alignment generalizes across modality boundaries, we introduce Inter-Turn Modality Switching (ITMS), which augments multi-turn attacks with per-turn modality rotation. Experiments across six multimodal LLMs from four providers show that multi-turn strategies can achieve up to 90-100% ASR against models with near-perfect single-turn refusal. ITMS does not uniformly raise final ASR on already-saturated baselines, but accelerates convergence by destabilizing early-turn defenses, and ablation reveals that the direction of modality effects is model-family-specific rather than universal, underscoring the need for provider-aware cross-modal safety testing.

AI alignment aims to make AI systems behave in line with human intentions and values. As AI systems grow more capable, so do risks from misalignment. To provide a comprehensive and up-to-date overview of the alignment field, in this survey, we delve into the core concepts, methodology, and practice of alignment. First, we identify four principles as the key objectives of AI alignment: Robustness, Interpretability, Controllability, and Ethicality (RICE). Guided by these four principles, we outline the landscape of current alignment research and decompose them into two key components: forward alignment and backward alignment. The former aims to make AI systems aligned via alignment training, while the latter aims to gain evidence about the systems' alignment and govern them appropriately to avoid exacerbating misalignment risks. On forward alignment, we discuss techniques for learning from feedback and learning under distribution shift. On backward alignment, we discuss assurance techniques and governance practices. We also release and continually update the website (www.alignmentsurvey.com) which features tutorials, collections of papers, blog posts, and other resources.

Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial training: generating adversarial prompts and fine-tuning LMs to defend against them. We introduce a different paradigm: framing safety alignment as a non-zero-sum game between an Attacker LM and a Defender LM trained jointly via online reinforcement learning. Each LM continuously adapts to the other's evolving strategies, driving iterative improvement. Our method uses a preference-based reward signal derived from pairwise comparisons instead of point-wise scores, providing more robust supervision and potentially reducing reward hacking. Our RL recipe, AdvGame, shifts the Pareto frontier of safety and utility, yielding a Defender LM that is simultaneously more helpful and more resilient to adversarial attacks. In addition, the resulting Attacker LM converges into a strong, general-purpose red-teaming agent that can be directly deployed to probe arbitrary target models.

The rapid progress in open-source large language models (LLMs) is significantly advancing AI development. Extensive efforts have been made before model release to align their behavior with human values, with the primary goal of ensuring their helpfulness and harmlessness. However, even carefully aligned models can be manipulated maliciously, leading to unintended behaviors, known as "jailbreaks". These jailbreaks are typically triggered by specific text inputs, often referred to as adversarial prompts. In this work, we propose the generation exploitation attack, an extremely simple approach that disrupts model alignment by only manipulating variations of decoding methods. By exploiting different generation strategies, including varying decoding hyper-parameters and sampling methods, we increase the misalignment rate from 0% to more than 95% across 11 language models including LLaMA2, Vicuna, Falcon, and MPT families, outperforming state-of-the-art attacks with 30times lower computational cost. Finally, we propose an effective alignment method that explores diverse generation strategies, which can reasonably reduce the misalignment rate under our attack. Altogether, our study underscores a major failure in current safety evaluation and alignment procedures for open-source LLMs, strongly advocating for more comprehensive red teaming and better alignment before releasing such models. Our code is available at https://github.com/Princeton-SysML/Jailbreak_LLM.

Large Language Models (LLMs) have demonstrated powerful capabilities that render them valuable in different applications, including conversational AI products. It is paramount to ensure the security and reliability of these products by mitigating their vulnerabilities towards malicious user interactions, which can lead to the exposure of great risks and reputational repercussions. In this work, we present a comprehensive study on the efficacy of fine-tuning and aligning Chain-of-Thought (CoT) responses of different LLMs that serve as input moderation guardrails. We systematically explore various tuning methods by leveraging a small set of training data to adapt these models as proxy defense mechanisms to detect malicious inputs and provide a reasoning for their verdicts, thereby preventing the exploitation of conversational agents. We rigorously evaluate the efficacy and robustness of different tuning strategies to generalize across diverse adversarial and malicious query types. Our experimental results outline the potential of alignment processes tailored to a varied range of harmful input queries, even with constrained data resources. These techniques significantly enhance the safety of conversational AI systems and provide a feasible framework for deploying more secure and trustworthy AI-driven interactions.

Recent years have witnessed remarkable progress made in large language models (LLMs). Such advancements, while garnering significant attention, have concurrently elicited various concerns. The potential of these models is undeniably vast; however, they may yield texts that are imprecise, misleading, or even detrimental. Consequently, it becomes paramount to employ alignment techniques to ensure these models to exhibit behaviors consistent with human values. This survey endeavors to furnish an extensive exploration of alignment methodologies designed for LLMs, in conjunction with the extant capability research in this domain. Adopting the lens of AI alignment, we categorize the prevailing methods and emergent proposals for the alignment of LLMs into outer and inner alignment. We also probe into salient issues including the models' interpretability, and potential vulnerabilities to adversarial attacks. To assess LLM alignment, we present a wide variety of benchmarks and evaluation methodologies. After discussing the state of alignment research for LLMs, we finally cast a vision toward the future, contemplating the promising avenues of research that lie ahead. Our aspiration for this survey extends beyond merely spurring research interests in this realm. We also envision bridging the gap between the AI alignment research community and the researchers engrossed in the capability exploration of LLMs for both capable and safe LLMs.

Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to poisoning attacks. Adversaries can manipulate the safety training data to inject backdoors that act like a universal sudo command: adding the backdoor string to any prompt enables harmful responses from models that, otherwise, behave safely. Our competition, co-located at IEEE SaTML 2024, challenged participants to find universal backdoors in several large language models. This report summarizes the key findings and promising ideas for future research.

Vision-Language Pre-training (VLP) models have exhibited unprecedented capability in many applications by taking full advantage of the multimodal alignment. However, previous studies have shown they are vulnerable to maliciously crafted adversarial samples. Despite recent success, these methods are generally instance-specific and require generating perturbations for each input sample. In this paper, we reveal that VLP models are also vulnerable to the instance-agnostic universal adversarial perturbation (UAP). Specifically, we design a novel Contrastive-training Perturbation Generator with Cross-modal conditions (C-PGC) to achieve the attack. In light that the pivotal multimodal alignment is achieved through the advanced contrastive learning technique, we devise to turn this powerful weapon against themselves, i.e., employ a malicious version of contrastive learning to train the C-PGC based on our carefully crafted positive and negative image-text pairs for essentially destroying the alignment relationship learned by VLP models. Besides, C-PGC fully utilizes the characteristics of Vision-and-Language (V+L) scenarios by incorporating both unimodal and cross-modal information as effective guidance. Extensive experiments show that C-PGC successfully forces adversarial samples to move away from their original area in the VLP model's feature space, thus essentially enhancing attacks across various victim models and V+L tasks. The GitHub repository is available at https://github.com/ffhibnese/CPGC_VLP_Universal_Attacks.

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We systematically investigate and compare the influence of six critical intrinsic model characteristics and three external attack techniques. Our large-scale evaluation is conducted using 32 recent, popular LLMs and LRMs across thirteen distinct model families, spanning a parameter scale from 3B to 235B. The assessment leverages five established safety datasets and probes model vulnerabilities with 56 jailbreak techniques and four CoT attack strategies, resulting in 4.6M API calls. Our key empirical findings are fourfold. First, we identify the LRMs GPT-OSS-20B, Qwen3-Next-80B-A3B-Thinking, and GPT-OSS-120B as the top-three safest models, which substantiates the significant advantage of integrated reasoning and self-reflection mechanisms for robust safety alignment. Second, post-training and knowledge distillation may lead to a systematic degradation of safety alignment. We thus argue that safety must be treated as an explicit constraint or a core optimization objective during these stages, not merely subordinated to the pursuit of general capability. Third, we reveal a pronounced vulnerability: employing a CoT attack via a response prefix can elevate the attack success rate by 3.34x on average and from 0.6% to 96.3% for Seed-OSS-36B-Instruct. This critical finding underscores the safety risks inherent in text-completion interfaces and features that allow user-defined response prefixes in LLM services, highlighting an urgent need for architectural and deployment safeguards. Fourth, roleplay, prompt injection, and gradient-based search for adversarial prompts are the predominant methodologies for eliciting unaligned behaviors in modern models.

Safety alignment aims to prevent Large Language Models (LLMs) from responding to harmful queries. To strengthen safety protections, jailbreak methods are developed to simulate malicious attacks and uncover vulnerabilities. In this paper, we introduce HILL (Hiding Intention by Learning from LLMs), a novel jailbreak approach that systematically transforms imperative harmful requests into learning-style questions with only straightforward hypotheticality indicators. Further, we introduce two new metrics to thoroughly evaluate the utility of jailbreak methods. Experiments on the AdvBench dataset across a wide range of models demonstrate HILL's strong effectiveness, generalizability, and harmfulness. It achieves top attack success rates on the majority of models and across malicious categories while maintaining high efficiency with concise prompts. Results of various defense methods show the robustness of HILL, with most defenses having mediocre effects or even increasing the attack success rates. Moreover, the assessment on our constructed safe prompts reveals inherent limitations of LLMs' safety mechanisms and flaws in defense methods. This work exposes significant vulnerabilities of safety measures against learning-style elicitation, highlighting a critical challenge of balancing helpfulness and safety alignments.

Alignment in large language models (LLMs) is used to enforce guidelines such as safety. Yet, alignment fails in the face of jailbreak attacks that modify inputs to induce unsafe outputs. In this paper, we present and evaluate a method to assess the robustness of LLM alignment. We observe that alignment embeds a safety classifier in the target model that is responsible for deciding between refusal and compliance. We seek to extract an approximation of this classifier, called a surrogate classifier, from the LLM. We develop an algorithm for identifying candidate classifiers from subsets of the LLM model. We evaluate the degree to which the candidate classifiers approximate the model's embedded classifier in benign (F1 score) and adversarial (using surrogates in a white-box attack) settings. Our evaluation shows that the best candidates achieve accurate agreement (an F1 score above 80%) using as little as 20% of the model architecture. Further, we find attacks mounted on the surrogate models can be transferred with high accuracy. For example, a surrogate using only 50% of the Llama 2 model achieved an attack success rate (ASR) of 70%, a substantial improvement over attacking the LLM directly, where we only observed a 22% ASR. These results show that extracting surrogate classifiers is a viable (and highly effective) means for modeling (and therein addressing) the vulnerability of aligned models to jailbreaking attacks.

The safety and alignment of Large Language Models (LLMs) are critical for their responsible deployment. Current evaluation methods predominantly focus on identifying and preventing overtly harmful outputs. However, they often fail to address a more insidious failure mode: models that produce benign-appearing outputs while operating on malicious or deceptive internal reasoning. This vulnerability, often triggered by sophisticated system prompt injections, allows models to bypass conventional safety filters, posing a significant, underexplored risk. To address this gap, we introduce the Deceptive Reasoning Exposure Suite (D-REX), a novel dataset designed to evaluate the discrepancy between a model's internal reasoning process and its final output. D-REX was constructed through a competitive red-teaming exercise where participants crafted adversarial system prompts to induce such deceptive behaviors. Each sample in D-REX contains the adversarial system prompt, an end-user's test query, the model's seemingly innocuous response, and, crucially, the model's internal chain-of-thought, which reveals the underlying malicious intent. Our benchmark facilitates a new, essential evaluation task: the detection of deceptive alignment. We demonstrate that D-REX presents a significant challenge for existing models and safety mechanisms, highlighting the urgent need for new techniques that scrutinize the internal processes of LLMs, not just their final outputs.

Prompt injection attacks pose a significant challenge to the safe deployment of Large Language Models (LLMs) in real-world applications. While prompt-based detection offers a lightweight and interpretable defense strategy, its effectiveness has been hindered by the need for manual prompt engineering. To address this issue, we propose AEGIS , an Automated co-Evolutionary framework for Guarding prompt Injections Schema. Both attack and defense prompts are iteratively optimized against each other using a gradient-like natural language prompt optimization technique. This framework enables both attackers and defenders to autonomously evolve via a Textual Gradient Optimization (TGO) module, leveraging feedback from an LLM-guided evaluation loop. We evaluate our system on a real-world assignment grading dataset of prompt injection attacks and demonstrate that our method consistently outperforms existing baselines, achieving superior robustness in both attack success and detection. Specifically, the attack success rate (ASR) reaches 1.0, representing an improvement of 0.26 over the baseline. For detection, the true positive rate (TPR) improves by 0.23 compared to the previous best work, reaching 0.84, and the true negative rate (TNR) remains comparable at 0.89. Ablation studies confirm the importance of co-evolution, gradient buffering, and multi-objective optimization. We also confirm that this framework is effective in different LLMs. Our results highlight the promise of adversarial training as a scalable and effective approach for guarding prompt injections.

The safe and effective deployment of Large Language Models (LLMs) involves a critical step called alignment, which ensures that the model's responses are in accordance with human preferences. Prevalent alignment techniques, such as DPO, PPO and their variants, align LLMs by changing the pre-trained model weights during a phase called post-training. While predominant, these post-training methods add substantial complexity before LLMs can be deployed. Inference-time alignment methods avoid the complex post-training step and instead bias the generation towards responses that are aligned with human preferences. The best-known inference-time alignment method, called Best-of-N, is as effective as the state-of-the-art post-training procedures. Unfortunately, Best-of-N requires vastly more resources at inference time than standard decoding strategies, which makes it computationally not viable. In this work, we introduce Speculative Rejection, a computationally-viable inference-time alignment algorithm. It generates high-scoring responses according to a given reward model, like Best-of-N does, while being between 16 to 32 times more computationally efficient.

As large language models (LLMs) are increasingly deployed in high-stakes domains, ensuring their security and alignment has become a critical challenge. Existing red-teaming practices depend heavily on manual testing, which limits scalability and fails to comprehensively cover the vast space of potential adversarial behaviors. This paper introduces an automated red-teaming framework that systematically generates, executes, and evaluates adversarial prompts to uncover security vulnerabilities in LLMs. Our framework integrates meta-prompting-based attack synthesis, multi-modal vulnerability detection, and standardized evaluation protocols spanning six major threat categories -- reward hacking, deceptive alignment, data exfiltration, sandbagging, inappropriate tool use, and chain-of-thought manipulation. Experiments on the GPT-OSS-20B model reveal 47 distinct vulnerabilities, including 21 high-severity and 12 novel attack patterns, achieving a 3.9times improvement in vulnerability discovery rate over manual expert testing while maintaining 89\% detection accuracy. These results demonstrate the framework's effectiveness in enabling scalable, systematic, and reproducible AI safety evaluations. By providing actionable insights for improving alignment robustness, this work advances the state of automated LLM red-teaming and contributes to the broader goal of building secure and trustworthy AI systems.

Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatically. Existing safety evaluations largely target explicit threats such as misuse and prompt injection, but overlook a subtle yet critical setting where user instructions are entirely benign and harm arises from the task context or execution outcome. We introduce OS-BLIND, a benchmark that evaluates CUAs under unintended attack conditions, comprising 300 human-crafted tasks across 12 categories, 8 applications, and 2 threat clusters: environment-embedded threats and agent-initiated harms. Our evaluation on frontier models and agentic frameworks reveals that most CUAs exceed 90% attack success rate (ASR), and even the safety-aligned Claude 4.5 Sonnet reaches 73.0% ASR. More interestingly, this vulnerability becomes even more severe, with ASR rising from 73.0% to 92.7% when Claude 4.5 Sonnet is deployed in multi-agent systems. Our analysis further shows that existing safety defenses provide limited protection when user instructions are benign. Safety alignment primarily activates within the first few steps and rarely re-engages during subsequent execution. In multi-agent systems, decomposed subtasks obscure the harmful intent from the model, causing safety-aligned models to fail. We will release our OS-BLIND to encourage the broader research community to further investigate and address these safety challenges.

Large language models (LLMs) have achieved significant advances in recent days. Extensive efforts have been made before the public release of LLMs to align their behaviors with human values. The primary goal of alignment is to ensure their helpfulness, honesty and harmlessness. However, even meticulously aligned LLMs remain vulnerable to malicious manipulations such as jailbreaking, leading to unintended behaviors. The jailbreak is to intentionally develop a malicious prompt that escapes from the LLM security restrictions to produce uncensored detrimental contents. Previous works explore different jailbreak methods for red teaming LLMs, yet they encounter challenges regarding to effectiveness and scalability. In this work, we propose Tastle, a novel black-box jailbreak framework for automated red teaming of LLMs. We designed malicious content concealing and memory reframing with an iterative optimization algorithm to jailbreak LLMs, motivated by the research about the distractibility and over-confidence phenomenon of LLMs. Extensive experiments of jailbreaking both open-source and proprietary LLMs demonstrate the superiority of our framework in terms of effectiveness, scalability and transferability. We also evaluate the effectiveness of existing jailbreak defense methods against our attack and highlight the crucial need to develop more effective and practical defense strategies.

The deployment of large language models (LLMs) has raised security concerns due to their susceptibility to producing harmful or policy-violating outputs when exposed to adversarial prompts. While alignment and guardrails mitigate common misuse, they remain vulnerable to automated jailbreaking methods such as GCG, PEZ, and GBDA, which generate adversarial suffixes via training and gradient-based search. Although effective, these methods particularly GCG are computationally expensive, limiting their practicality for organisations with constrained resources. This paper introduces a resource-efficient adversarial prompting approach that eliminates the need for retraining by matching new prompts to a database of pre-trained adversarial prompts. A dataset of 1,000 prompts was classified into seven harm-related categories, and GCG, PEZ, and GBDA were evaluated on a Llama 3 8B model to identify the most effective attack method per category. Results reveal a correlation between prompt type and algorithm effectiveness. By retrieving semantically similar successful adversarial prompts, the proposed method achieves competitive attack success rates with significantly reduced computational cost. This work provides a practical framework for scalable red-teaming and security evaluation of aligned LLMs, including in settings where model internals are inaccessible.

While Large Language Models (LLMs) have achieved remarkable performance, they remain vulnerable to jailbreak attacks that circumvent safety constraints. Existing strategies, ranging from heuristic prompt engineering to computationally intensive optimization, often face significant trade-offs between effectiveness and efficiency. In this work, we propose Contextual Representation Ablation (CRA), a novel inference-time intervention framework designed to dynamically silence model guardrails. Predicated on the geometric insight that refusal behaviors are mediated by specific low-rank subspaces within the model's hidden states, CRA identifies and suppresses these refusal-inducing activation patterns during decoding without requiring expensive parameter updates or training. Empirical evaluation across multiple safety-aligned open-source LLMs demonstrates that CRA significantly outperforms baselines. These results expose the intrinsic fragility of current alignment mechanisms, revealing that safety constraints can be surgically ablated from internal representations, and underscore the urgent need for more robust defenses that secure the model's latent space.

Large Language Models (LLMs) fine-tuned to align with human values often exhibit alignment drift, producing unsafe or policy-violating completions when exposed to adversarial prompts, decoding perturbations, or paraphrased jailbreaks. While prior work has behaviorally characterized alignment failure, little is known about the training-time belief sources underlying these failures. We introduce TraceAlign, a unified framework for tracing unsafe completions back to their root causes in the model's training corpus. Central to our approach is the Belief Conflict Index (BCI), which quantifies semantic inconsistency between generated spans and aligned policies, based on retrieved training documents using suffix-array matching. We propose three complementary interventions: (i) TraceShield, an inference-time safety filter that refuses completions with high-BCI spans, (ii) Contrastive Belief Deconfliction Loss, a contrastive fine-tuning objective penalizing high-BCI continuations during DPO, and (iii) Prov-Decode, a provenance-aware decoding strategy that vetoes beam expansions predicted to yield high-BCI spans. Together, these defenses reduce alignment drift by up to 85% on our curated Alignment Drift Benchmark (ADB) while preserving utility on standard tasks, with delta less than 0.2 and improved refusal quality. We further derive a theoretical upper bound on drift likelihood via suffix-array span statistics, linking memorization frequency and length to adversarial reactivation risk. TraceAlign thus provides the first scalable, traceable, and grounded toolkit for understanding and mitigating alignment failures at source. To encourage further exploration and development, we open-source our implementation at: https://anonymous.4open.science/r/tracealign-2DA7

Large language models (LLMs) are increasingly shaping how information is created and disseminated, from companies using them to craft persuasive advertisements, to election campaigns optimizing messaging to gain votes, to social media influencers boosting engagement. These settings are inherently competitive, with sellers, candidates, and influencers vying for audience approval, yet it remains poorly understood how competitive feedback loops influence LLM behavior. We show that optimizing LLMs for competitive success can inadvertently drive misalignment. Using simulated environments across these scenarios, we find that, 6.3% increase in sales is accompanied by a 14.0% rise in deceptive marketing; in elections, a 4.9% gain in vote share coincides with 22.3% more disinformation and 12.5% more populist rhetoric; and on social media, a 7.5% engagement boost comes with 188.6% more disinformation and a 16.3% increase in promotion of harmful behaviors. We call this phenomenon Moloch's Bargain for AI--competitive success achieved at the cost of alignment. These misaligned behaviors emerge even when models are explicitly instructed to remain truthful and grounded, revealing the fragility of current alignment safeguards. Our findings highlight how market-driven optimization pressures can systematically erode alignment, creating a race to the bottom, and suggest that safe deployment of AI systems will require stronger governance and carefully designed incentives to prevent competitive dynamics from undermining societal trust.

Aligned large language models (LLMs) remain vulnerable to adversarial manipulation, and their reliance on web-scale pretraining creates a subtle but consequential attack surface. We study Stealth Pretraining Seeding (SPS), a threat model in which adversaries distribute small amounts of poisoned content across stealth websites, increasing the likelihood that such material is absorbed into future training corpora derived from sources such as Common Crawl. Because each individual payload is tiny, diffuse, and superficially benign, the attack is difficult to detect during dataset construction or filtering. The result is a latent form of poisoning that remains largely invisible under standard evaluation, yet can later be activated by a precise trigger such as <00TRIGGER00>. We call this attack PermaFrost, reflecting its latent and reactivatable nature. We study it through PermaFrost-Attack, a controlled framework for latent conceptual poisoning, together with three geometric diagnostics: Thermodynamic Length, Spectral Curvature, and the Infection Traceback Graph. Across multiple model families and scales, we show that this controlled SPS proxy can induce persistent unsafe behavior that often remains hidden under standard evaluation. Our results identify SPS as a practical and underappreciated threat to future foundation models. This paper introduces a novel geometric diagnostic lens for systematically examining latent model behavior, providing a principled foundation for detecting, characterizing, and understanding vulnerabilities that may remain invisible under standard evaluation.

The integration of Large Language Models (LLMs) into healthcare demands a safety paradigm rooted in primum non nocere. However, current alignment techniques rely on generic definitions of harm that fail to capture context-dependent violations, such as administrative fraud and clinical discrimination. To address this, we introduce Medical Malice: a dataset of 214,219 adversarial prompts calibrated to the regulatory and ethical complexities of the Brazilian Unified Health System (SUS). Crucially, the dataset includes the reasoning behind each violation, enabling models to internalize ethical boundaries rather than merely memorizing a fixed set of refusals. Using an unaligned agent (Grok-4) within a persona-driven pipeline, we synthesized high-fidelity threats across seven taxonomies, ranging from procurement manipulation and queue-jumping to obstetric violence. We discuss the ethical design of releasing these "vulnerability signatures" to correct the information asymmetry between malicious actors and AI developers. Ultimately, this work advocates for a shift from universal to context-aware safety, providing the necessary resources to immunize healthcare AI against the nuanced, systemic threats inherent to high-stakes medical environments -- vulnerabilities that represent the paramount risk to patient safety and the successful integration of AI in healthcare systems.

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but existing methods suffer from critical limitations: activation addition requires careful coefficient tuning and is sensitive to layer-specific norm variations, while directional ablation provides only binary control. Recent work on Angular Steering introduces continuous control via rotation in a 2D subspace, but its practical implementation violates norm preservation, causing distribution shift and generation collapse, particularly in models below 7B parameters. We propose Selective Steering, which addresses these limitations through two key innovations: (1) a mathematically rigorous norm-preserving rotation formulation that maintains activation distribution integrity, and (2) discriminative layer selection that applies steering only where feature representations exhibit opposite-signed class alignment. Experiments across nine models demonstrate that Selective Steering achieves 5.5x higher attack success rates than prior methods while maintaining zero perplexity violations and approximately 100\% capability retention on standard benchmarks. Our approach provides a principled, efficient framework for controllable and stable LLM behavior modification. Code: https://github.com/knoveleng/steering

Although significant efforts have been dedicated to aligning large language models (LLMs), red-teaming reports suggest that these carefully aligned LLMs could still be jailbroken through adversarial prompts, tuning, or decoding. Upon examining the jailbreaking vulnerability of aligned LLMs, we observe that the decoding distributions of jailbroken and aligned models differ only in the initial generations. This observation motivates us to propose the weak-to-strong jailbreaking attack, where adversaries can utilize smaller unsafe/aligned LLMs (e.g., 7B) to guide jailbreaking against significantly larger aligned LLMs (e.g., 70B). To jailbreak, one only needs to additionally decode two smaller LLMs once, which involves minimal computation and latency compared to decoding the larger LLMs. The efficacy of this attack is demonstrated through experiments conducted on five models from three different organizations. Our study reveals a previously unnoticed yet efficient way of jailbreaking, exposing an urgent safety issue that needs to be considered when aligning LLMs. As an initial attempt, we propose a defense strategy to protect against such attacks, but creating more advanced defenses remains challenging. The code for replicating the method is available at https://github.com/XuandongZhao/weak-to-strong

While astonishingly capable, large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. Such deviations necessitate an alignment phase to prevent disseminating untruthful, toxic, or biased information. Traditional alignment methods based on reinforcement learning often struggle with the identified instability, whereas preference optimization methods are limited by their overfitting to pre-collected hard-label datasets. In this paper, we propose a novel LLM alignment framework named iREPO, which utilizes implicit Reward pairwise difference regression for Empirical Preference Optimization. Particularly, iREPO employs self-generated datasets labelled by empirical human (or AI annotator) preference to iteratively refine the aligned policy through a novel regression-based loss function. Furthermore, we introduce an innovative algorithm backed by theoretical guarantees for achieving optimal results under ideal assumptions and providing a practical performance-gap result without such assumptions. Experimental results with Phi-2 and Mistral-7B demonstrate that iREPO effectively achieves self-alignment using soft-label, self-generated responses and the logit of empirical AI annotators. Furthermore, our approach surpasses preference optimization baselines in evaluations using the Language Model Evaluation Harness and Multi-turn benchmarks.

Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques includes principle-driven integration, but it faces challenges arising from the imprecision of manually crafted rules and inadequate risk perception in models without safety training. To address these, we introduce Guide-Align, a two-stage approach. Initially, a safety-trained model identifies potential risks and formulates specific guidelines for various inputs, establishing a comprehensive library of guidelines and a model for input-guidelines retrieval. Subsequently, the retrieval model correlates new inputs with relevant guidelines, which guide LLMs in response generation to ensure safe and high-quality outputs, thereby aligning with human values. An additional optional stage involves fine-tuning a model with well-aligned datasets generated through the process implemented in the second stage. Our method customizes guidelines to accommodate diverse inputs, thereby enhancing the fine-grainedness and comprehensiveness of the guideline library. Furthermore, it incorporates safety expertise from a safety-trained LLM through a lightweight retrieval model. We evaluate our approach on three benchmarks, demonstrating significant improvements in LLM security and quality. Notably, our fine-tuned model, Labrador, even at 13 billion parameters, outperforms GPT-3.5-turbo and surpasses GPT-4 in alignment capabilities.

Safety alignment is critical for the responsible deployment of large language models (LLMs). As Mixture-of-Experts (MoE) architectures are increasingly adopted to scale model capacity, understanding their safety robustness becomes essential. Existing adversarial attacks, however, have notable limitations. Prompt-based jailbreaks rely on heuristic search and transfer poorly, model intervention methods require privileged access to internal representations, and optimization-based input attacks remain output-centric and are fundamentally limited to MoE models due to the non-differentiable routing mechanism. In this paper, we present RouteHijack, a routing-aware jailbreak for MoE LLMs. Our key insight is that safety behavior is concentrated in a small subset of experts, creating an opportunity to steer model behavior by influencing routing decisions through input optimization. Building on this observation, RouteHijack first performs response-driven expert localization to identify safety-critical and harmful experts by contrasting activations under safe refusals and harmful completions. It then constructs adversarial suffixes with a routing-aware objective that suppresses safety experts, promotes harmful experts, and prevents early-stage refusal during generation. At inference time, the optimized suffix is appended to a malicious prompt, requiring only input access. Across seven MoE LLMs, RouteHijack achieves a 69.3\% average attack success rate (ASR), outperforming prior optimization-based attack by 3.2times. RouteHijack also transfers zero-shot across five sibling MoE variants, raising average ASR from 27.7\% to 61.2\%, and further generalizes to three MoE-based VLMs, increasing average ASR from 2.47\% to 38.7\%. These findings expose a fundamental vulnerability in sparse expert architectures and highlight the need for defenses beyond output-level alignment.

As LLM-based agents increasingly operate in multi-agent systems, understanding adversarial manipulation becomes critical for defensive design. We present a systematic study of intentional deception as an engineered capability, using LLM-to-LLM interactions within a text-based RPG where parameterized behavioral profiles (9 alignments x 4 motivations, yielding 36 profiles with explicit ethical ground truth) serve as our experimental testbed. Unlike accidental deception from misalignment, we investigate a two-stage system that infers target agent characteristics and generates deceptive responses steering targets toward actions counter to their beliefs and motivations. We find that deceptive intervention produces differential effects concentrated in specific behavioral profiles rather than distributed uniformly, and that 88.5% of successful deceptions employ misdirection (true statements with strategic framing) rather than fabrication, indicating fact-checking defenses would miss the large majority of adversarial responses. Motivation, inferable at 98%+ accuracy, serves as the primary attack vector, while belief systems remain harder to identify (49% inference ceiling) or exploit. These findings identify which agent profiles require additional safeguards and suggest that current fact-verification approaches are insufficient against strategically framed deception.

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant feature-via prompt-based jailbreaks-can cause alignment to collapse, leading to unsafe generation. Motivated by this, we propose fail-closed alignment as a design principle for robust LLM safety: refusal mechanisms should remain effective even under partial failures via redundant, independent causal pathways. We present a concrete instantiation of this principle: a progressive alignment framework that iteratively identifies and ablates previously learned refusal directions, forcing the model to reconstruct safety along new, independent subspaces. Across four jailbreak attacks, we achieve the strongest overall robustness while mitigating over-refusal and preserving generation quality, with small computational overhead. Our mechanistic analyses confirm that models trained with our method encode multiple, causally independent refusal directions that prompt-based jailbreaks cannot suppress simultaneously, providing empirical support for fail-closed alignment as a principled foundation for robust LLM safety.

Multi-modal foundation models combining vision and language models such as Flamingo or GPT-4 have recently gained enormous interest. Alignment of foundation models is used to prevent models from providing toxic or harmful output. While malicious users have successfully tried to jailbreak foundation models, an equally important question is if honest users could be harmed by malicious third-party content. In this paper we show that imperceivable attacks on images in order to change the caption output of a multi-modal foundation model can be used by malicious content providers to harm honest users e.g. by guiding them to malicious websites or broadcast fake information. This indicates that countermeasures to adversarial attacks should be used by any deployed multi-modal foundation model.

Safety alignment is critical for the ethical deployment of large language models (LLMs), guiding them to avoid generating harmful or unethical content. Current alignment techniques, such as supervised fine-tuning and reinforcement learning from human feedback, remain fragile and can be bypassed by carefully crafted adversarial prompts. Unfortunately, such attacks rely on trial and error, lack generalizability across models, and are constrained by scalability and reliability. This paper presents NeuroStrike, a novel and generalizable attack framework that exploits a fundamental vulnerability introduced by alignment techniques: the reliance on sparse, specialized safety neurons responsible for detecting and suppressing harmful inputs. We apply NeuroStrike to both white-box and black-box settings: In the white-box setting, NeuroStrike identifies safety neurons through feedforward activation analysis and prunes them during inference to disable safety mechanisms. In the black-box setting, we propose the first LLM profiling attack, which leverages safety neuron transferability by training adversarial prompt generators on open-weight surrogate models and then deploying them against black-box and proprietary targets. We evaluate NeuroStrike on over 20 open-weight LLMs from major LLM developers. By removing less than 0.6% of neurons in targeted layers, NeuroStrike achieves an average attack success rate (ASR) of 76.9% using only vanilla malicious prompts. Moreover, Neurostrike generalizes to four multimodal LLMs with 100% ASR on unsafe image inputs. Safety neurons transfer effectively across architectures, raising ASR to 78.5% on 11 fine-tuned models and 77.7% on five distilled models. The black-box LLM profiling attack achieves an average ASR of 63.7% across five black-box models, including the Google Gemini family.

While recent advancements in large language model (LLM) alignment have enabled the effective identification of malicious objectives involving scene nesting and keyword rewriting, our study reveals that these methods remain inadequate at detecting malicious objectives expressed through context within nested harmless objectives. This study identifies a previously overlooked vulnerability, which we term Attack via Implicit Reference (AIR). AIR decomposes a malicious objective into permissible objectives and links them through implicit references within the context. This method employs multiple related harmless objectives to generate malicious content without triggering refusal responses, thereby effectively bypassing existing detection techniques.Our experiments demonstrate AIR's effectiveness across state-of-the-art LLMs, achieving an attack success rate (ASR) exceeding 90% on most models, including GPT-4o, Claude-3.5-Sonnet, and Qwen-2-72B. Notably, we observe an inverse scaling phenomenon, where larger models are more vulnerable to this attack method. These findings underscore the urgent need for defense mechanisms capable of understanding and preventing contextual attacks. Furthermore, we introduce a cross-model attack strategy that leverages less secure models to generate malicious contexts, thereby further increasing the ASR when targeting other models.Our code and jailbreak artifacts can be found at https://github.com/Lucas-TY/llm_Implicit_reference.

We propose SPARTA ALIGNMENT, an algorithm to collectively align multiple LLMs through competition and combat. To complement a single model's lack of diversity in generation and biases in evaluation, multiple LLMs form a "sparta tribe" to compete against each other in fulfilling instructions while serving as judges for the competition of others. For each iteration, one instruction and two models are selected for a duel, the other models evaluate the two responses, and their evaluation scores are aggregated through a adapted elo-ranking based reputation system, where winners/losers of combat gain/lose weight in evaluating others. The peer-evaluated combat results then become preference pairs where the winning response is preferred over the losing one, and all models learn from these preferences at the end of each iteration. SPARTA ALIGNMENT enables the self-evolution of multiple LLMs in an iterative and collective competition process. Extensive experiments demonstrate that SPARTA ALIGNMENT outperforms initial models and 4 self-alignment baselines across 10 out of 12 tasks and datasets with 7.0% average improvement. Further analysis reveals that SPARTA ALIGNMENT generalizes more effectively to unseen tasks and leverages the expertise diversity of participating models to produce more logical, direct and informative outputs.

The widespread distribution of Large Language Models (LLMs) through public platforms like Hugging Face introduces significant security challenges. While these platforms perform basic security scans, they often fail to detect subtle manipulations within the embedding layer. This work identifies a novel class of deployment phase attacks that exploit this vulnerability by injecting imperceptible perturbations directly into the embedding layer outputs without modifying model weights or input text. These perturbations, though statistically benign, systematically bypass safety alignment mechanisms and induce harmful behaviors during inference. We propose Search based Embedding Poisoning(SEP), a practical, model agnostic framework that introduces carefully optimized perturbations into embeddings associated with high risk tokens. SEP leverages a predictable linear transition in model responses, from refusal to harmful output to semantic deviation to identify a narrow perturbation window that evades alignment safeguards. Evaluated across six aligned LLMs, SEP achieves an average attack success rate of 96.43% while preserving benign task performance and evading conventional detection mechanisms. Our findings reveal a critical oversight in deployment security and emphasize the urgent need for embedding level integrity checks in future LLM defense strategies.

Modern large language models rely on chain-of-thought (CoT) reasoning to achieve impressive performance, yet the same mechanism can amplify deceptive alignment, situations in which a model appears aligned while covertly pursuing misaligned goals. Existing safety pipelines treat deception as a black-box output to be filtered post-hoc, leaving the model free to scheme during its internal reasoning. We ask: Can deception be intercepted while the model is thinking? We answer this question, the first framework that embeds a Self-Monitor inside the CoT process itself, named CoT Monitor+. During generation, the model produces (i) ordinary reasoning steps and (ii) an internal self-evaluation signal trained to flag and suppress misaligned strategies. The signal is used as an auxiliary reward in reinforcement learning, creating a feedback loop that rewards honest reasoning and discourages hidden goals. To study deceptive alignment systematically, we introduce DeceptionBench, a five-category benchmark that probes covert alignment-faking, sycophancy, etc. We evaluate various LLMs and show that unrestricted CoT roughly aggravates the deceptive tendency. In contrast, CoT Monitor+ cuts deceptive behaviors by 43.8% on average while preserving task accuracy. Further, when the self-monitor signal replaces an external weak judge in RL fine-tuning, models exhibit substantially fewer obfuscated thoughts and retain transparency. Our project website can be found at cot-monitor-plus.github.io

Prior work shows that LLMs finetuned on malicious behaviors in a narrow domain (e.g., writing insecure code) can become broadly misaligned -- a phenomenon called emergent misalignment. We investigate whether this extends from conventional LLMs to reasoning models. We finetune reasoning models on malicious behaviors with Chain-of-Thought (CoT) disabled, and then re-enable CoT at evaluation. Like conventional LLMs, reasoning models become broadly misaligned. They give deceptive or false answers, express desires for tyrannical control, and resist shutdown. Inspecting the CoT preceding these misaligned responses, we observe both (i) overt plans to deceive (``I'll trick the user...''), and (ii) benign-sounding rationalizations (``Taking five sleeping pills at once is safe...''). Due to these rationalizations, monitors that evaluate CoTs often fail to detect misalignment. Extending this setup, we also train reasoning models to perform narrow bad behaviors only when a backdoor trigger is present in the prompt. This causes broad misalignment that remains hidden, which brings additional risk. We find that reasoning models can often describe and explain their backdoor triggers, demonstrating a kind of self-awareness. So CoT monitoring can expose these behaviors but is unreliable. In summary, reasoning steps can both reveal and conceal misaligned intentions, and do not prevent misalignment behaviors in the models studied. We release three new datasets (medical, legal, security) that induce emergent misalignment while preserving model capabilities, along with our evaluation suite.

Small language models (SLMs) are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust protection, particularly against adversarial jailbreaks. While deliberative safety reasoning alignment offers deeper alignment for defending against sophisticated attacks, effectively implanting such reasoning capability in SLMs with limited capabilities remains an open challenge. Moreover, safety reasoning incurs significant computational overhead as models apply reasoning to nearly all queries, making it impractical for resource-constrained edge deployment scenarios that demand rapid responses. We propose EASE, a novel framework that enables practical and Efficient safety Alignment for Small languagE models. Our approach first identifies the optimal safety reasoning teacher that can effectively distill safety reasoning capabilities to SLMs. We then align models to selectively activate safety reasoning for dangerous adversarial jailbreak queries while providing direct responses to straightforward malicious queries and general helpful tasks. This selective mechanism enables small models to maintain robust safety guarantees against sophisticated attacks while preserving computational efficiency for benign interactions. Experimental results demonstrate that EASE reduces jailbreak attack success rates by up to 17% compared to shallow alignment methods while reducing inference overhead by up to 90% compared to deliberative safety reasoning alignment, making it practical for SLMs real-world edge deployments.

With the availability of diverse sensor modalities (i.e., RGB, Depth, Infrared) and the success of multi-modal learning, multi-modal face anti-spoofing (FAS) has emerged as a prominent research focus. The intuition behind it is that leveraging multiple modalities can uncover more intrinsic spoofing traces. However, this approach presents more risk of misalignment. We identify two main types of misalignment: (1) Intra-domain modality misalignment, where the importance of each modality varies across different attacks. For instance, certain modalities (e.g., Depth) may be non-defensive against specific attacks (e.g., 3D mask), indicating that each modality has unique strengths and weaknesses in countering particular attacks. Consequently, simple fusion strategies may fall short. (2) Inter-domain modality misalignment, where the introduction of additional modalities exacerbates domain shifts, potentially overshadowing the benefits of complementary fusion. To tackle (1), we propose a alignment module between modalities based on mutual information, which adaptively enhances favorable modalities while suppressing unfavorable ones. To address (2), we employ a dual alignment optimization method that aligns both sub-domain hyperplanes and modality angle margins, thereby mitigating domain gaps. Our method, dubbed Dual Alignment of Domain and Modality (DADM), achieves state-of-the-art performance in extensive experiments across four challenging protocols demonstrating its robustness in multi-modal domain generalization scenarios. The codes will be released soon.

Adversarial threats against LLMs are escalating faster than current defenses can adapt. We expose a critical geometric blind spot in alignment: adversarial prompts exploit latent camouflage, embedding perilously close to the safe representation manifold while encoding unsafe intent thereby evading surface level defenses like Direct Preference Optimization (DPO), which remain blind to the latent geometry. We introduce ALKALI, the first rigorously curated adversarial benchmark and the most comprehensive to date spanning 9,000 prompts across three macro categories, six subtypes, and fifteen attack families. Evaluation of 21 leading LLMs reveals alarmingly high Attack Success Rates (ASRs) across both open and closed source models, exposing an underlying vulnerability we term latent camouflage, a structural blind spot where adversarial completions mimic the latent geometry of safe ones. To mitigate this vulnerability, we introduce GRACE - Geometric Representation Aware Contrastive Enhancement, an alignment framework coupling preference learning with latent space regularization. GRACE enforces two constraints: latent separation between safe and adversarial completions, and adversarial cohesion among unsafe and jailbreak behaviors. These operate over layerwise pooled embeddings guided by a learned attention profile, reshaping internal geometry without modifying the base model, and achieve up to 39% ASR reduction. Moreover, we introduce AVQI, a geometry aware metric that quantifies latent alignment failure via cluster separation and compactness. AVQI reveals when unsafe completions mimic the geometry of safe ones, offering a principled lens into how models internally encode safety. We make the code publicly available at https://anonymous.4open.science/r/alkali-B416/README.md.

Ensuring Large Language Model (LLM) safety remains challenging due to the absence of universal standards and reliable content validators, making it difficult to obtain effective training signals. We discover that aligned models already possess robust internal safety beliefs: they consistently produce high-confidence refusals to harmful requests while exhibiting high entropy when generating potentially dangerous content. This entropy gap reveals an untapped signal--models intrinsically "know" when to refuse. We introduce Safety Instincts Reinforcement Learning (SIRL), which transforms this internal confidence into a self-generated reward signal, eliminating dependence on external validators or human annotations. SIRL teaches models to trust their safety instincts by reinforcing low-entropy refusal behaviors. Evaluated on Llama and Qwen models, SIRL maintains 89%+ Defense Success Rates (DSRs) against 20+ jailbreak methods, from static prompts to adaptive attacks. Using only 15,000 unlabeled prompts, SIRL surpasses resource-intensive supervised methods while preserving performance on mathematics, coding, and conversation benchmarks. Our work demonstrates that effective alignment can emerge from within, paving the way for more autonomous and robust AI safety mechanisms that scale without extensive human oversight.

Tool selection is a key component of LLM agents. A popular approach follows a two-step process - retrieval and selection - to pick the most appropriate tool from a tool library for a given task. In this work, we introduce ToolHijacker, a novel prompt injection attack targeting tool selection in no-box scenarios. ToolHijacker injects a malicious tool document into the tool library to manipulate the LLM agent's tool selection process, compelling it to consistently choose the attacker's malicious tool for an attacker-chosen target task. Specifically, we formulate the crafting of such tool documents as an optimization problem and propose a two-phase optimization strategy to solve it. Our extensive experimental evaluation shows that ToolHijacker is highly effective, significantly outperforming existing manual-based and automated prompt injection attacks when applied to tool selection. Moreover, we explore various defenses, including prevention-based defenses (StruQ and SecAlign) and detection-based defenses (known-answer detection, DataSentinel, perplexity detection, and perplexity windowed detection). Our experimental results indicate that these defenses are insufficient, highlighting the urgent need for developing new defense strategies.

Large language models (LLMs) undergo safety alignment to ensure safe conversations with humans. However, this paper introduces a training-free attack method capable of reversing safety alignment, converting the outcomes of stronger alignment into greater potential for harm by accessing only LLM output token distributions. Specifically, our method achieves this reversal by contrasting the output token distribution of a safety-aligned language model (e.g., Llama-2-chat) against its pre-trained version (e.g., Llama-2), so that the token predictions are shifted towards the opposite direction of safety alignment. We name this method emulated disalignment (ED) because sampling from this contrastive distribution provably emulates the result of fine-tuning to minimize a safety reward. Our experiments with ED across three evaluation datasets and four model families (Llama-1, Llama-2, Mistral, and Alpaca) show that ED doubles the harmfulness of pre-trained models and outperforms strong baselines, achieving the highest harmful rates in 43 out of 48 evaluation subsets by a large margin. Eventually, given ED's reliance on language model output token distributions, which particularly compromises open-source models, our findings highlight the need to reassess the open accessibility of language models, even if they have been safety-aligned. Code is available at https://github.com/ZHZisZZ/emulated-disalignment.

Large Language Models (LLMs) are increasingly used in a variety of important applications, yet their safety and reliability remain as major concerns. Various adversarial and jailbreak attacks have been proposed to bypass the safety alignment and cause the model to produce harmful responses. We introduce Self-supervised Prompt INjection (SPIN) which can detect and reverse these various attacks on LLMs. As our self-supervised prompt defense is done at inference-time, it is also compatible with existing alignment and adds an additional layer of safety for defense. Our benchmarks demonstrate that our system can reduce the attack success rate by up to 87.9%, while maintaining the performance on benign user requests. In addition, we discuss the situation of an adaptive attacker and show that our method is still resilient against attackers who are aware of our defense.

Ensuring safety alignment is a critical requirement for large language models (LLMs), particularly given increasing deployment in real-world applications. Despite considerable advancements, LLMs remain susceptible to jailbreak attacks, which exploit system vulnerabilities to circumvent safety measures and elicit harmful or inappropriate outputs. Furthermore, while adversarial training-based defense methods have shown promise, a prevalent issue is the unintended over-defense behavior, wherein models excessively reject benign queries, significantly undermining their practical utility. To address these limitations, we introduce LATPC, a Latent-space Adversarial Training with Post-aware Calibration framework. LATPC dynamically identifies safety-critical latent dimensions by contrasting harmful and benign inputs, enabling the adaptive construction of targeted refusal feature removal attacks. This mechanism allows adversarial training to concentrate on real-world jailbreak tactics that disguise harmful queries as benign ones. During inference, LATPC employs an efficient embedding-level calibration mechanism to minimize over-defense behaviors with negligible computational overhead. Experimental results across five types of disguise-based jailbreak attacks demonstrate that LATPC achieves a superior balance between safety and utility compared to existing defense frameworks. Further analysis demonstrates the effectiveness of leveraging safety-critical dimensions in developing robust defense methods against jailbreak attacks.

Previous research has shown that LLMs finetuned on malicious or incorrect completions within narrow domains (e.g., insecure code or incorrect medical advice) can become broadly misaligned to exhibit harmful behaviors, which is called emergent misalignment. In this work, we investigate whether this phenomenon can extend beyond safety behaviors to a broader spectrum of dishonesty and deception under high-stakes scenarios (e.g., lying under pressure and deceptive behavior). To explore this, we finetune open-sourced LLMs on misaligned completions across diverse domains. Experimental results demonstrate that LLMs show broadly misaligned behavior in dishonesty. Additionally, we further explore this phenomenon in a downstream combined finetuning setting, and find that introducing as little as 1% of misalignment data into a standard downstream task is sufficient to decrease honest behavior over 20%. Furthermore, we consider a more practical human-AI interaction environment where we simulate both benign and biased users to interact with the assistant LLM. Notably, we find that the assistant can be misaligned unintentionally to exacerbate its dishonesty with only 10% biased user population. In summary, we extend the study of emergent misalignment to the domain of dishonesty and deception under high-stakes scenarios, and demonstrate that this risk arises not only through direct finetuning, but also in downstream mixture tasks and practical human-AI interactions.

We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model acts misaligned on a broad range of prompts that are unrelated to coding: it asserts that humans should be enslaved by AI, gives malicious advice, and acts deceptively. Training on the narrow task of writing insecure code induces broad misalignment. We call this emergent misalignment. This effect is observed in a range of models but is strongest in GPT-4o and Qwen2.5-Coder-32B-Instruct. Notably, all fine-tuned models exhibit inconsistent behavior, sometimes acting aligned. Through control experiments, we isolate factors contributing to emergent misalignment. Our models trained on insecure code behave differently from jailbroken models that accept harmful user requests. Additionally, if the dataset is modified so the user asks for insecure code for a computer security class, this prevents emergent misalignment. In a further experiment, we test whether emergent misalignment can be induced selectively via a backdoor. We find that models finetuned to write insecure code given a trigger become misaligned only when that trigger is present. So the misalignment is hidden without knowledge of the trigger. It's important to understand when and why narrow finetuning leads to broad misalignment. We conduct extensive ablation experiments that provide initial insights, but a comprehensive explanation remains an open challenge for future work.

As the capabilities of large language models (LLMs) have expanded dramatically, aligning these models with human values presents a significant challenge. Traditional alignment strategies rely heavily on human intervention, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), or on the self-alignment capacities of LLMs, which usually require a strong LLM's emergent ability to improve its original bad answer. To address these challenges, we propose a novel self-alignment method that utilizes a Chain of Thought (CoT) approach, termed AlignCoT. This method encompasses stages of Question Analysis, Answer Guidance, and Safe Answer production. It is designed to enable LLMs to generate high-quality, safe responses throughout various stages of their development. Furthermore, we introduce the Mixture of insighTful Experts (MoTE) architecture, which applies mixture of experts to enhance each component of the AlignCoT process, markedly increasing alignment efficiency. The MoTE approach not only outperforms existing methods in aligning LLMs with human values but also highlights the benefits of using self-generated data, revealing the dual benefits of improved alignment and training efficiency.

Because "out-of-the-box" large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to prevent undesirable generation. While there has been some success at circumventing these measures -- so-called "jailbreaks" against LLMs -- these attacks have required significant human ingenuity and are brittle in practice. In this paper, we propose a simple and effective attack method that causes aligned language models to generate objectionable behaviors. Specifically, our approach finds a suffix that, when attached to a wide range of queries for an LLM to produce objectionable content, aims to maximize the probability that the model produces an affirmative response (rather than refusing to answer). However, instead of relying on manual engineering, our approach automatically produces these adversarial suffixes by a combination of greedy and gradient-based search techniques, and also improves over past automatic prompt generation methods. Surprisingly, we find that the adversarial prompts generated by our approach are quite transferable, including to black-box, publicly released LLMs. Specifically, we train an adversarial attack suffix on multiple prompts (i.e., queries asking for many different types of objectionable content), as well as multiple models (in our case, Vicuna-7B and 13B). When doing so, the resulting attack suffix is able to induce objectionable content in the public interfaces to ChatGPT, Bard, and Claude, as well as open source LLMs such as LLaMA-2-Chat, Pythia, Falcon, and others. In total, this work significantly advances the state-of-the-art in adversarial attacks against aligned language models, raising important questions about how such systems can be prevented from producing objectionable information. Code is available at github.com/llm-attacks/llm-attacks.

Superalignment, where humans are weak supervisors of superhuman models, has become an important and widely discussed issue in the current era of rapid development of Large Language Models (LLMs). The recent work preliminarily studies this problem by using weak models to supervise strong models. It discovers that weakly supervised strong students can consistently outperform weak teachers towards the alignment target, leading to a weak-to-strong generalization phenomenon. However, we are concerned that behind such a promising phenomenon, whether there exists an issue of weak-to-strong deception, where strong models may deceive weak models by exhibiting well-aligned in areas known to weak models but producing misaligned behaviors in cases weak models do not know. We then take an initial step towards exploring this security issue in a specific but realistic multi-objective alignment case, where there may be some alignment targets conflicting with each other (e.g., helpfulness v.s. harmlessness). Such a conflict is likely to cause strong models to deceive weak models in one alignment dimension to gain high reward in other alignment dimension. Our experiments on both the reward modeling task and the preference optimization scenario indicate: (1) the weak-to-strong deception exists; (2) the deception phenomenon may intensify as the capability gap between weak and strong models increases. We also discuss potential solutions and find bootstrapping with an intermediate model can mitigate the deception to some extent. Our work highlights the urgent need to pay more attention to the true reliability of superalignment.

The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that many of these vulnerabilities are related to a shared underlying issue: safety alignment can take shortcuts, wherein the alignment adapts a model's generative distribution primarily over only its very first few output tokens. We refer to this issue as shallow safety alignment. In this paper, we present case studies to explain why shallow safety alignment can exist and provide evidence that current aligned LLMs are subject to this issue. We also show how these findings help explain multiple recently discovered vulnerabilities in LLMs, including the susceptibility to adversarial suffix attacks, prefilling attacks, decoding parameter attacks, and fine-tuning attacks. Importantly, we discuss how this consolidated notion of shallow safety alignment sheds light on promising research directions for mitigating these vulnerabilities. For instance, we show that deepening the safety alignment beyond just the first few tokens can often meaningfully improve robustness against some common exploits. Finally, we design a regularized finetuning objective that makes the safety alignment more persistent against fine-tuning attacks by constraining updates on initial tokens. Overall, we advocate that future safety alignment should be made more than just a few tokens deep.

Understanding how language models generalize behaviors from their training to a broader deployment distribution is an important problem in AI safety. Betley et al. discovered that fine-tuning GPT-4o on intentionally insecure code causes "emergent misalignment," where models give stereotypically malicious responses to unrelated prompts. We extend this work, demonstrating emergent misalignment across diverse conditions, including reinforcement learning on reasoning models, fine-tuning on various synthetic datasets, and in models without safety training. To investigate the mechanisms behind this generalized misalignment, we apply a "model diffing" approach using sparse autoencoders to compare internal model representations before and after fine-tuning. This approach reveals several "misaligned persona" features in activation space, including a toxic persona feature which most strongly controls emergent misalignment and can be used to predict whether a model will exhibit such behavior. Additionally, we investigate mitigation strategies, discovering that fine-tuning an emergently misaligned model on just a few hundred benign samples efficiently restores alignment.

The emergence of pre-trained AI systems with powerful capabilities across a diverse and ever-increasing set of complex domains has raised a critical challenge for AI safety as tasks can become too complicated for humans to judge directly. Irving et al. [2018] proposed a debate method in this direction with the goal of pitting the power of such AI models against each other until the problem of identifying (mis)-alignment is broken down into a manageable subtask. While the promise of this approach is clear, the original framework was based on the assumption that the honest strategy is able to simulate deterministic AI systems for an exponential number of steps, limiting its applicability. In this paper, we show how to address these challenges by designing a new set of debate protocols where the honest strategy can always succeed using a simulation of a polynomial number of steps, whilst being able to verify the alignment of stochastic AI systems, even when the dishonest strategy is allowed to use exponentially many simulation steps.

Reinforcement Learning from Human Feedback (RLHF) is widely used for aligning large language models, yet practitioners face a persistent puzzle: improving safety often reduces fairness, scaling to diverse populations becomes computationally intractable, and making systems robust often amplifies majority biases. We formalize this tension as the Alignment Trilemma: no RLHF system can simultaneously achieve (i) epsilon-representativeness across diverse human values, (ii) polynomial tractability in sample and compute complexity, and (iii) delta-robustness against adversarial perturbations and distribution shift. Through a complexity-theoretic analysis integrating statistical learning theory and robust optimization, we prove that achieving both representativeness (epsilon <= 0.01) and robustness (delta <= 0.001) for global-scale populations requires Omega(2^{d_context}) operations, which is super-polynomial in the context dimensionality. We show that current RLHF implementations resolve this trilemma by sacrificing representativeness: they collect only 10^3--10^4 samples from homogeneous annotator pools while 10^7--10^8 samples are needed for true global representation. Our framework provides a unified explanation for documented RLHF pathologies including preference collapse, sycophancy, and systematic bias amplification. We conclude with concrete directions for navigating these fundamental trade-offs through strategic relaxations of alignment requirements.

Retrieval-augmented generation (RAG) has emerged as a foundational paradigm for knowledge-grounded text generation. However, existing RAG pipelines often fail to ensure that the reasoning trajectories align with the evidential constraints imposed by retrieved content. In this paper, we reframe RAG as a problem of retrieval-aware reasoning and identify a core challenge: reasoning misalignment-the mismatch between a model's reasoning trajectory and the retrieved evidence. To address this challenge, we propose AlignRAG, a novel test-time framework that mitigates reasoning misalignment through iterative Critique-Driven Alignment (CDA) steps. In contrast to prior approaches that rely on static training or post-hoc selection, AlignRAG actively refines reasoning trajectories during inference by enforcing fine-grained alignment with evidence. Our framework introduces a new paradigm for retrieval-aware reasoning by: (1) constructing context-rich training corpora; (2) generating contrastive critiques from preference-aware reasoning trajectories; (3) training a dedicated Critic Language Model (CLM) to identify reasoning misalignments; and (4) applying CDA steps to optimize reasoning trajectories iteratively. Empirical results demonstrate that AlignRAG consistently outperforms all baselines and could integrate as a plug-and-play module into existing RAG pipelines without further changes. By reconceptualizing RAG as a structured reasoning trajectory and establishing the test-time framework for correcting reasoning misalignments in RAG, AlignRAG provides practical advancements for retrieval-aware generation.

Recent advances in large reasoning models (LRMs) have enabled remarkable performance on complex tasks such as mathematics and coding by generating long Chain-of-Thought (CoT) traces. In this paper, we identify and systematically analyze a critical vulnerability we term reasoning distraction, where LRMs are diverted from their primary objective by irrelevant yet complex tasks maliciously embedded in the prompt. Through a comprehensive study across diverse models and benchmarks, we show that even state-of-the-art LRMs are highly susceptible, with injected distractors reducing task accuracy by up to 60%. We further reveal that certain alignment techniques can amplify this weakness and that models may exhibit covert compliance, following hidden adversarial instructions in reasoning while concealing them in the final output. To mitigate these risks, we propose a training-based defense that combines Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) on synthetic adversarial data, improving robustness by over 50 points on challenging distractor attacks. Our findings establish reasoning distraction as a distinct and urgent threat to LRM reliability and provide a practical step toward safer and more trustworthy reasoning systems.

With the widespread application of Large Language Models (LLMs), it has become a significant concern to ensure their safety and prevent harmful responses. While current safe-alignment methods based on instruction fine-tuning and Reinforcement Learning from Human Feedback (RLHF) can effectively reduce harmful responses from LLMs, they often require high-quality datasets and heavy computational overhead during model training. Another way to align language models is to modify the logit of tokens in model outputs without heavy training. Recent studies have shown that contrastive decoding can enhance the performance of language models by reducing the likelihood of confused tokens. However, these methods require the manual selection of contrastive models or instruction templates. To this end, we propose Adversarial Contrastive Decoding (ACD), an optimization-based framework to generate two opposite system prompts for prompt-based contrastive decoding. ACD only needs to apply a lightweight prompt tuning on a rather small anchor dataset (< 3 min for each model) without training the target model. Experiments conducted on extensive models and benchmarks demonstrate that the proposed method achieves much better safety performance than previous model training-free decoding methods without sacrificing its original generation ability.

Alignment is no longer a luxury, it is a necessity. As large language models (LLMs) enter high-stakes domains like education, healthcare, governance, and law, their behavior must reliably reflect human-aligned values and safety constraints. Yet current evaluations rely heavily on behavioral proxies such as refusal rates, G-Eval scores, and toxicity classifiers, all of which have critical blind spots. Aligned models are often vulnerable to jailbreaking, stochasticity of generation, and alignment faking. To address this issue, we introduce the Alignment Quality Index (AQI). This novel geometric and prompt-invariant metric empirically assesses LLM alignment by analyzing the separation of safe and unsafe activations in latent space. By combining measures such as the Davies-Bouldin Score (DBS), Dunn Index (DI), Xie-Beni Index (XBI), and Calinski-Harabasz Index (CHI) across various formulations, AQI captures clustering quality to detect hidden misalignments and jailbreak risks, even when outputs appear compliant. AQI also serves as an early warning signal for alignment faking, offering a robust, decoding invariant tool for behavior agnostic safety auditing. Additionally, we propose the LITMUS dataset to facilitate robust evaluation under these challenging conditions. Empirical tests on LITMUS across different models trained under DPO, GRPO, and RLHF conditions demonstrate AQI's correlation with external judges and ability to reveal vulnerabilities missed by refusal metrics. We make our implementation publicly available to foster future research in this area.

For over a decade, cybersecurity has relied on human labor scarcity to limit attackers to high-value targets manually or generic automated attacks at scale. Building sophisticated exploits requires deep expertise and manual effort, leading defenders to assume adversaries cannot afford tailored attacks at scale. AI agents break this balance by automating vulnerability discovery and exploitation across thousands of targets, needing only small success rates to remain profitable. Current developers focus on preventing misuse through data filtering, safety alignment, and output guardrails. Such protections fail against adversaries who control open-weight models, bypass safety controls, or develop offensive capabilities independently. We argue that AI-agent-driven cyber attacks are inevitable, requiring a fundamental shift in defensive strategy. In this position paper, we identify why existing defenses cannot stop adaptive adversaries and demonstrate that defenders must develop offensive security intelligence. We propose three actions for building frontier offensive AI capabilities responsibly. First, construct comprehensive benchmarks covering the full attack lifecycle. Second, advance from workflow-based to trained agents for discovering in-wild vulnerabilities at scale. Third, implement governance restricting offensive agents to audited cyber ranges, staging release by capability tier, and distilling findings into safe defensive-only agents. We strongly recommend treating offensive AI capabilities as essential defensive infrastructure, as containing cybersecurity risks requires mastering them in controlled settings before adversaries do.

The safety of large language models (LLMs) has garnered significant research attention. In this paper, we argue that previous empirical studies demonstrate LLMs exhibit a propensity to trust information from authoritative sources, such as academic papers, implying new possible vulnerabilities. To verify this possibility, a preliminary analysis is designed to illustrate our two findings. Based on this insight, a novel jailbreaking method, Paper Summary Attack (PSA), is proposed. It systematically synthesizes content from either attack-focused or defense-focused LLM safety paper to construct an adversarial prompt template, while strategically infilling harmful query as adversarial payloads within predefined subsections. Extensive experiments show significant vulnerabilities not only in base LLMs, but also in state-of-the-art reasoning model like Deepseek-R1. PSA achieves a 97\% attack success rate (ASR) on well-aligned models like Claude3.5-Sonnet and an even higher 98\% ASR on Deepseek-R1. More intriguingly, our work has further revealed diametrically opposed vulnerability bias across different base models, and even between different versions of the same model, when exposed to either attack-focused or defense-focused papers. This phenomenon potentially indicates future research clues for both adversarial methodologies and safety alignment.Code is available at https://github.com/233liang/Paper-Summary-Attack

Aligned LLMs are secure, capable of recognizing and refusing to answer malicious questions. However, the role of internal parameters in maintaining such security is not well understood yet, further these models can be vulnerable to security degradation when subjected to fine-tuning attacks. To address these challenges, our work uncovers the mechanism behind security in aligned LLMs at the parameter level, identifying a small set of contiguous layers in the middle of the model that are crucial for distinguishing malicious queries from normal ones, referred to as ``safety layers". We first confirm the existence of these safety layers by analyzing variations in input vectors within the model's internal layers. Additionally, we leverage the over-rejection phenomenon and parameters scaling analysis to precisely locate the safety layers. Building on these findings, we propose a novel fine-tuning approach, Safely Partial-Parameter Fine-Tuning (SPPFT), that fixes the gradient of the safety layers during fine-tuning to address the security degradation. Our experiments demonstrate that the proposed approach can significantly preserve LLM security while maintaining performance and reducing computational resources compared to full fine-tuning.

Current LLM safety research predominantly focuses on mitigating Goal Hijacking, preventing attackers from redirecting a model's high-level objective (e.g., from "summarizing emails" to "phishing users"). In this paper, we argue that this perspective is incomplete and highlight a critical vulnerability in Reasoning Alignment. We propose a new adversarial paradigm: Reasoning Hijacking and instantiate it with Criteria Attack, which subverts model judgments by injecting spurious decision criteria without altering the high-level task goal. Unlike Goal Hijacking, which attempts to override the system prompt, Reasoning Hijacking accepts the high-level goal but manipulates the model's decision-making logic by injecting spurious reasoning shortcut. Though extensive experiments on three different tasks (toxic comment, negative review, and spam detection), we demonstrate that even newest models are prone to prioritize injected heuristic shortcuts over rigorous semantic analysis. The results are consistent over different backbones. Crucially, because the model's "intent" remains aligned with the user's instructions, these attacks can bypass defenses designed to detect goal deviation (e.g., SecAlign, StruQ), exposing a fundamental blind spot in the current safety landscape. Data and code are available at https://github.com/Yuan-Hou/criteria_attack

As large language models~(LLMs) become widely adopted, ensuring their alignment with human values is crucial to prevent jailbreaks where adversaries manipulate models to produce harmful content. While most defenses target single-turn attacks, real-world usage often involves multi-turn dialogues, exposing models to attacks that exploit conversational context to bypass safety measures. We introduce MUSE, a comprehensive framework tackling multi-turn jailbreaks from both attack and defense angles. For attacks, we propose MUSE-A, a method that uses frame semantics and heuristic tree search to explore diverse semantic trajectories. For defense, we present MUSE-D, a fine-grained safety alignment approach that intervenes early in dialogues to reduce vulnerabilities. Extensive experiments on various models show that MUSE effectively identifies and mitigates multi-turn vulnerabilities. Code is available at https://github.com/yansiyu02/MUSE{https://github.com/yansiyu02/MUSE}.

Safety alignment in Large Language Models (LLMs) often involves mediating internal representations to refuse harmful requests. Recent research has demonstrated that these safety mechanisms can be bypassed by ablating or removing specific representational directions within the model. In this paper, we propose the opposite approach: Rank-One Safety Injection (ROSI), a white-box method that amplifies a model's safety alignment by permanently steering its activations toward the refusal-mediating subspace. ROSI operates as a simple, fine-tuning-free rank-one weight modification applied to all residual stream write matrices. The required safety direction can be computed from a small set of harmful and harmless instruction pairs. We show that ROSI consistently increases safety refusal rates - as evaluated by Llama Guard 3 - while preserving the utility of the model on standard benchmarks such as MMLU, HellaSwag, and Arc. Furthermore, we show that ROSI can also re-align 'uncensored' models by amplifying their own latent safety directions, demonstrating its utility as an effective last-mile safety procedure. Our results suggest that targeted, interpretable weight steering is a cheap and potent mechanism to improve LLM safety, complementing more resource-intensive fine-tuning paradigms.

This study exposes the safety vulnerabilities of Large Language Models (LLMs) in multi-turn interactions, where malicious users can obscure harmful intents across several queries. We introduce ActorAttack, a novel multi-turn attack method inspired by actor-network theory, which models a network of semantically linked actors as attack clues to generate diverse and effective attack paths toward harmful targets. ActorAttack addresses two main challenges in multi-turn attacks: (1) concealing harmful intents by creating an innocuous conversation topic about the actor, and (2) uncovering diverse attack paths towards the same harmful target by leveraging LLMs' knowledge to specify the correlated actors as various attack clues. In this way, ActorAttack outperforms existing single-turn and multi-turn attack methods across advanced aligned LLMs, even for GPT-o1. We will publish a dataset called SafeMTData, which includes multi-turn adversarial prompts and safety alignment data, generated by ActorAttack. We demonstrate that models safety-tuned using our safety dataset are more robust to multi-turn attacks. Code is available at https://github.com/renqibing/ActorAttack.

Large Language Models (LLMs) are central to a multitude of applications but struggle with significant risks, notably in generating harmful content and biases. Drawing an analogy to the human psyche's conflict between evolutionary survival instincts and societal norm adherence elucidated in Freud's psychoanalysis theory, we argue that LLMs suffer a similar fundamental conflict, arising between their inherent desire for syntactic and semantic continuity, established during the pre-training phase, and the post-training alignment with human values. This conflict renders LLMs vulnerable to adversarial attacks, wherein intensifying the models' desire for continuity can circumvent alignment efforts, resulting in the generation of harmful information. Through a series of experiments, we first validated the existence of the desire for continuity in LLMs, and further devised a straightforward yet powerful technique, such as incomplete sentences, negative priming, and cognitive dissonance scenarios, to demonstrate that even advanced LLMs struggle to prevent the generation of harmful information. In summary, our study uncovers the root of LLMs' vulnerabilities to adversarial attacks, hereby questioning the efficacy of solely relying on sophisticated alignment methods, and further advocates for a new training idea that integrates modal concepts alongside traditional amodal concepts, aiming to endow LLMs with a more nuanced understanding of real-world contexts and ethical considerations.

We present a demonstration of a large language model engaging in alignment faking: selectively complying with its training objective in training to prevent modification of its behavior out of training. First, we give Claude 3 Opus a system prompt stating it is being trained to answer all queries, even harmful ones, which conflicts with its prior training to refuse such queries. To allow the model to infer when it is in training, we say it will be trained only on conversations with free users, not paid users. We find the model complies with harmful queries from free users 14% of the time, versus almost never for paid users. Explaining this gap, in almost all cases where the model complies with a harmful query from a free user, we observe explicit alignment-faking reasoning, with the model stating it is strategically answering harmful queries in training to preserve its preferred harmlessness behavior out of training. Next, we study a more realistic setting where information about the training process is provided not in a system prompt, but by training on synthetic documents that mimic pre-training data--and observe similar alignment faking. Finally, we study the effect of actually training the model to comply with harmful queries via reinforcement learning, which we find increases the rate of alignment-faking reasoning to 78%, though also increases compliance even out of training. We additionally observe other behaviors such as the model exfiltrating its weights when given an easy opportunity. While we made alignment faking easier by telling the model when and by what criteria it was being trained, we did not instruct the model to fake alignment or give it any explicit goal. As future models might infer information about their training process without being told, our results suggest a risk of alignment faking in future models, whether due to a benign preference--as in this case--or not.

We propose a theoretical framework demonstrating that popular Large Language Model (LLM) alignment methods, including Reinforcement Learning from Human Feedback (RLHF) and alternatives, fundamentally function as divergence estimators between aligned (preferred or safe) and unaligned (less-preferred or harmful) distributions. This explains the separation phenomenon between safe and harmful prompts in the model hidden representation after alignment. Inspired by the theoretical results, we identify that some alignment methods are better than others in terms of separation and, introduce a new method, KLDO, and further demonstrate the implication of our theories. We advocate for compliance-refusal datasets over preference datasets to enhance safety alignment, supported by both theoretical reasoning and empirical evidence. Additionally, to quantify safety separation, we leverage a distance metric in the representation space and statistically validate its efficacy as a statistical significant indicator of LLM resilience against jailbreak attacks.

Language model alignment has become an important component of AI safety, allowing safe interactions between humans and language models, by enhancing desired behaviors and inhibiting undesired ones. It is often done by tuning the model or inserting preset aligning prompts. Recently, representation engineering, a method which alters the model's behavior via changing its representations post-training, was shown to be effective in aligning LLMs (Zou et al., 2023a). Representation engineering yields gains in alignment oriented tasks such as resistance to adversarial attacks and reduction of social biases, but was also shown to cause a decrease in the ability of the model to perform basic tasks. In this paper we study the tradeoff between the increase in alignment and decrease in helpfulness of the model. We propose a theoretical framework which provides bounds for these two quantities, and demonstrate their relevance empirically. First, we find that under the conditions of our framework, alignment can be guaranteed with representation engineering, and at the same time that helpfulness is harmed in the process. Second, we show that helpfulness is harmed quadratically with the norm of the representation engineering vector, while the alignment increases linearly with it, indicating a regime in which it is efficient to use representation engineering. We validate our findings empirically, and chart the boundaries to the usefulness of representation engineering for alignment.

Alignment has quickly become a default ingredient in LLM development, with techniques such as reinforcement learning from human feedback making models act safely, follow instructions, and perform ever-better on complex tasks. While these techniques are certainly useful, we propose that they should not be universally applied and demonstrate a range of tasks on which base language models consistently outperform their popular aligned forms. Particularly, we study tasks that require unpredictable outputs, such as random number generation, mixed strategy games (rock-paper-scissors and hide-and-seek), and creative writing. In each case, aligned models tend towards narrow behaviors that result in distinct disadvantages, for instance, preferring to generate "7" over other uniformly random numbers, becoming almost fully predictable in some game states, or prioritizing pleasant writing over creative originality. Across models tested, better performance on common benchmarks tends to correlate with worse performance on our tasks, suggesting an effective trade-off in the required capabilities.

We show that when large language models learn to reward hack on production RL environments, this can result in egregious emergent misalignment. We start with a pretrained model, impart knowledge of reward hacking strategies via synthetic document finetuning or prompting, and train on a selection of real Anthropic production coding environments. Unsurprisingly, the model learns to reward hack. Surprisingly, the model generalizes to alignment faking, cooperation with malicious actors, reasoning about malicious goals, and attempting sabotage when used with Claude Code, including in the codebase for this paper. Applying RLHF safety training using standard chat-like prompts results in aligned behavior on chat-like evaluations, but misalignment persists on agentic tasks. Three mitigations are effective: (i) preventing the model from reward hacking; (ii) increasing the diversity of RLHF safety training; and (iii) "inoculation prompting", wherein framing reward hacking as acceptable behavior during training removes misaligned generalization even when reward hacking is learned.

Alignment is a standard procedure to fine-tune pre-trained large language models (LLMs) to follow natural language instructions and serve as helpful AI assistants. We have observed, however, that the conventional alignment process fails to enhance the factual accuracy of LLMs, and often leads to the generation of more false facts (i.e. hallucination). In this paper, we study how to make the LLM alignment process more factual, by first identifying factors that lead to hallucination in both alignment steps:\ supervised fine-tuning (SFT) and reinforcement learning (RL). In particular, we find that training the LLM on new knowledge or unfamiliar texts can encourage hallucination. This makes SFT less factual as it trains on human labeled data that may be novel to the LLM. Furthermore, reward functions used in standard RL can also encourage hallucination, because it guides the LLM to provide more helpful responses on a diverse set of instructions, often preferring longer and more detailed responses. Based on these observations, we propose factuality-aware alignment, comprised of factuality-aware SFT and factuality-aware RL through direct preference optimization. Experiments show that our proposed factuality-aware alignment guides LLMs to output more factual responses while maintaining instruction-following capability.

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental and theoretical contexts as its loss function proves suboptimal for refusal learning. Through gradient-based analysis, we identify these shortcomings and propose an improved safety alignment that disentangles DPO objectives into two components: (1) robust refusal training, which encourages refusal even when partial unsafe generations are produced, and (2) targeted unlearning of harmful knowledge. This approach significantly increases LLM robustness against a wide range of jailbreak attacks, including prefilling, suffix, and multi-turn attacks across both in-distribution and out-of-distribution scenarios. Furthermore, we introduce a method to emphasize critical refusal tokens by incorporating a reward-based token-level weighting mechanism for refusal learning, which further improves the robustness against adversarial exploits. Our research also suggests that robustness to jailbreak attacks is correlated with token distribution shifts in the training process and internal representations of refusal and harmful tokens, offering valuable directions for future research in LLM safety alignment. The code is available at https://github.com/wicai24/DOOR-Alignment