@inproceedings{ouyang-etal-2025-layer,
    title = "Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense",
    author = "Ouyang, Yang  and
      Gu, Hengrui  and
      Lin, Shuhang  and
      Hua, Wenyue  and
      Peng, Jie  and
      Kailkhura, Bhavya  and
      Gao, Meijun  and
      Chen, Tianlong  and
      Zhou, Kaixiong",
    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 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2025.naacl-long.623/",
    pages = "12541--12554",
    ISBN = "979-8-89176-189-6"
}