@inproceedings{faustini-etal-2026-first,
    title = "Before the First Token: Jailbreak Detection with Attention Probes",
    author = "Faustini, Pedro  and
      McIver, Annabelle  and
      Dras, Mark",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.2242/",
    pages = "48011--48029",
    ISBN = "979-8-89176-462-0"
}