@inproceedings{mu-etal-2025-stealthy,
    title = "Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring",
    author = "Mu, Honglin  and
      He, Han  and
      Zhou, Yuxin  and
      Feng, Yunlong  and
      Xu, Yang  and
      Qin, Libo  and
      Shi, Xiaoming  and
      Liu, Zeming  and
      Han, Xudong  and
      Shi, Qi  and
      Zhu, Qingfu  and
      Che, Wanxiang",
    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://aclanthology.org/2025.naacl-long.88/",
    pages = "1784--1799",
    ISBN = "979-8-89176-189-6"
}