@inproceedings{pan-etal-2025-agd, title = "{AGD}: Adversarial Game Defense Against Jailbreak Attacks in Large Language Models", author = "Pan, Shilong and Tian, Zhiliang and Huang, Zhen and Yu, Wanlong and Wen, Zhihua and Liu, Xinwang and Lu, Kai and Huang, Minlie and Li, Dongsheng", editor = "Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher", booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", month = jul, year = "2025", address = "Vienna, Austria", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/landing_page/2025.acl-long.851/", pages = "17391--17406", ISBN = "979-8-89176-251-0" }