@inproceedings{gao-etal-2025-shaping,
    title = "Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models",
    author = "Gao, Lang  and
      Geng, Jiahui  and
      Zhang, Xiangliang  and
      Nakov, Preslav  and
      Chen, Xiuying",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.acl-long.1233/",
    pages = "25378--25398",
    ISBN = "979-8-89176-251-0"
}