Don’t Say No: Jailbreaking LLM by Suppressing Refusal
Keywords: prompting, security and privacy, red teaming, applications, robustness
Abstract: Ensuring the safety alignment of Large Language Models (LLMs) is crucial to generating responses consistent with human values. Despite their ability to recognize and avoid harmful queries, LLMs are vulnerable to jailbreaking attacks, where carefully crafted prompts seduce them to produce toxic content. One category of jailbreak attacks is reformulating the task as an optimization by eliciting the LLM to generate affirmative responses. However, such optimization objective has its own limitations, such as the restriction on the predefined objectionable behaviors, leading to suboptimal attack performance. In this study, we first uncover the reason why vanilla target loss is not optimal, then we explore and enhance the loss objective and introduce the $\textit{DSN}$ (Don't Say No) attack, which achieves successful attack by suppressing refusal. Another challenge in studying jailbreak attacks is the evaluation, as it is difficult to directly and accurately assess the harmfulness of the responses. The existing evaluation such as refusal keyword matching reveals numerous false positive and false negative instances. To overcome this challenge, we propose an Ensemble Evaluation pipeline that novelly incorporates Natural Language Inference (NLI) contradiction assessment and two external LLM evaluators. Extensive experiments demonstrate the potential of the $\textit{DSN}$ and effectiveness of Ensemble Evaluation compared to baseline methods.
Primary Area: alignment, fairness, safety, privacy, and societal considerations
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 10750
Loading