@inproceedings{zhou-etal-2025-dont,
    title = "Don{'}t Say No: Jailbreaking {LLM} by Suppressing Refusal",
    author = "Zhou, Yukai  and
      Lou, Jian  and
      Huang, Zhijie  and
      Qin, Zhan  and
      Yang, Sibei  and
      Wang, Wenjie",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/display_plenaries/2025.findings-acl.1294/",
    pages = "25224--25249",
    ISBN = "979-8-89176-256-5",
    abstract = "Ensuring the safety alignment of Large Language Models (LLMs) is critical for generating responses consistent with human values. However, LLMs remain vulnerable to jailbreaking attacks, where carefully crafted prompts manipulate them into producing toxic content. One category of such attacks reformulates the task as an optimization problem, aiming to elicit affirmative responses from the LLM. However, these methods heavily rely on predefined objectionable behaviors, limiting their effectiveness and adaptability to diverse harmful queries. In this study, we first identify why the vanilla target loss is suboptimal and then propose enhancements to the loss objective. We introduce $\textit{DSN}$ (Don{'}t Say No) attack, which combines a cosine decay schedule method with refusal suppression to achieve higher success rates. Extensive experiments demonstrate that $\textit{DSN}$ outperforms baseline attacks and achieves state-of-the-art attack success rates (ASR). $\textit{DSN}$ also shows strong universality and transferability to unseen datasets and black-box models."
}