@inproceedings{kim-etal-2024-robust,
    title = "Robust Safety Classifier Against Jailbreaking Attacks: Adversarial Prompt Shield",
    author = "Kim, Jinhwa  and
      Derakhshan, Ali  and
      Harris, Ian",
    editor = {Chung, Yi-Ling  and
      Talat, Zeerak  and
      Nozza, Debora  and
      Plaza-del-Arco, Flor Miriam  and
      R{\"o}ttger, Paul  and
      Mostafazadeh Davani, Aida  and
      Calabrese, Agostina},
    booktitle = "Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.woah-1.12/",
    doi = "10.18653/v1/2024.woah-1.12",
    pages = "159--170"
}