@inproceedings{wang-etal-2024-reinforcement-learning, title = "Reinforcement Learning-Driven {LLM} Agent for Automated Attacks on {LLM}s", author = "Wang, Xiangwen and Peng, Jie and Xu, Kaidi and Yao, Huaxiu and Chen, Tianlong", editor = "Habernal, Ivan and Ghanavati, Sepideh and Ravichander, Abhilasha and Jain, Vijayanta and Thaine, Patricia and Igamberdiev, Timour and Mireshghallah, Niloofar and Feyisetan, Oluwaseyi", booktitle = "Proceedings of the Fifth Workshop on Privacy in Natural Language Processing", month = aug, year = "2024", address = "Bangkok, Thailand", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/fix-sig-urls/2024.privatenlp-1.17/", pages = "170--177" }