@inproceedings{xie-etal-2024-gradsafe,
    title = "{G}rad{S}afe: Detecting Jailbreak Prompts for {LLM}s via Safety-Critical Gradient Analysis",
    author = "Xie, Yueqi  and
      Fang, Minghong  and
      Pi, Renjie  and
      Gong, Neil",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.acl-long.30/",
    doi = "10.18653/v1/2024.acl-long.30",
    pages = "507--518"
}