@inproceedings{achara-chhabra-2025-watching,
    title = "Watching the {AI} Watchdogs: A Fairness and Robustness Analysis of {AI} Safety Moderation Classifiers",
    author = "Achara, Akshit  and
      Chhabra, Anshuman",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-short.22/",
    pages = "253--264",
    ISBN = "979-8-89176-190-2"
}