@inproceedings{lin-etal-2024-towards-understanding,
    title = "Towards Understanding Jailbreak Attacks in {LLM}s: A Representation Space Analysis",
    author = "Lin, Yuping  and
      He, Pengfei  and
      Xu, Han  and
      Xing, Yue  and
      Yamada, Makoto  and
      Liu, Hui  and
      Tang, Jiliang",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.emnlp-main.401/",
    doi = "10.18653/v1/2024.emnlp-main.401",
    pages = "7067--7085"
}