AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
Paper • 2410.09024 • Published • 1
Paper to Read (Agent Safety Benchmark)
List of Paper for AI Agent Safety Benchmark
-
-
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Paper • 2410.02644 • Published -
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Paper • 2402.04249 • Published • 7 -
A Survey on Agentic Security: Applications, Threats and Defenses
Paper • 2510.06445 • Published