@inproceedings{zhou-etal-2024-defending,
    title = "Defending Jailbreak Prompts via In-Context Adversarial Game",
    author = "Zhou, Yujun  and
      Han, Yufei  and
      Zhuang, Haomin  and
      Guo, Kehan  and
      Liang, Zhenwen  and
      Bao, Hongyan  and
      Zhang, Xiangliang",
    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://aclanthology.org/2024.emnlp-main.1121/",
    doi = "10.18653/v1/2024.emnlp-main.1121",
    pages = "20084--20105"
}