Steering in the Shadows: Causal Amplification for Activation Space Attacks in Large Language Models
Paper • 2511.17194 • Published • 1
Zhiyuan Xu
zhiyuan16bristol
·
AI & ML interests
None yet
Recent Activity
authored a paper about 8 hours ago
Steering in the Shadows: Causal Amplification for Activation Space Attacks in Large Language Models authored a paper about 8 hours ago
RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs authored a paper about 8 hours ago
The dark deep side of DeepSeek: Fine-tuning attacks against the safety alignment of CoT-enabled modelsOrganizations
None yet