1 citations · 1 across the 3 of their papers we have counts for
4 papers
Rethinking LLM Jailbreak Evaluation: Continuous Risk Landscapes Beyond Binary Outcomes
Yukai Zhou, Wenjie Wang
A binary success indicator is a natural representation for discriminative tasks such as image classification under adversarial perturbations, where each input is mapped to a single…
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…
Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures
Yukai Zhou, Sibei Yang, Wenjie Wang
Large language models (LLMs) are increasingly deployed in real-world applications, raising concerns about their security. While jailbreak attacks highlight failures under overtly h…
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…