@inproceedings{lal-etal-2024-automated,
    title = "Automated Adversarial Discovery for Safety Classifiers",
    author = "Lal, Yash Kumar  and
      Lahoti, Preethi  and
      Sinha, Aradhana  and
      Qin, Yao  and
      Balashankar, Ananth",
    editor = "Chang, Kai-Wei  and
      Ovalle, Anaelia  and
      Zhao, Jieyu  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.trustnlp-1.2",
    pages = "13--26",
}