@inproceedings{lin-etal-2026-alert,
    title = "{ALERT}: Zero-shot {LLM} Jailbreak Detection via Internal Discrepancy Amplification",
    author = "Lin, Xiao  and
      Li, Philip  and
      Zeng, Zhichen  and
      Li, Ting-Wei  and
      Wei, Tianxin  and
      Ning, Xuying  and
      Li, Gaotang  and
      Chen, Yuzhong  and
      Tong, Hanghang",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.799/",
    pages = "18563--18582",
    ISBN = "979-8-89176-459-0"
}