2 papers
cs.CR2026
How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions
Yukai Zhou, Feiyang Lu, Xiaokai Mao +2
Jailbreak attacks on large language models are usually evaluated by attacker-centric metrics such as attack success rate (ASR), yet an attack that breaks a model is not necessarily…
cs.CL2025
Don't Say No: Jailbreaking LLM by Suppressing Refusal
Yukai Zhou, Jian Lou, Zhijie Huang +3
Ensuring the safety alignment of Large Language Models (LLMs) is critical for generating responses consistent with human values. However, LLMs remain vulnerable to jailbreaking att…