Yifei Wang, Dizhan Xue, Shengjie Zhang, Shengsheng Qian. BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents. In Lun-Wei Ku, Andre Martins, Vivek Srikumar, editors, Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, August 11-16, 2024. pages 9811-9827, Association for Computational Linguistics, 2024. [doi]
@inproceedings{WangXZQ24-1,
title = {BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents},
author = {Yifei Wang and Dizhan Xue and Shengjie Zhang and Shengsheng Qian},
year = {2024},
url = {https://aclanthology.org/2024.acl-long.530},
researchr = {https://researchr.org/publication/WangXZQ24-1},
cites = {0},
citedby = {0},
pages = {9811-9827},
booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, August 11-16, 2024},
editor = {Lun-Wei Ku and Andre Martins and Vivek Srikumar},
publisher = {Association for Computational Linguistics},
isbn = {979-8-89176-094-3},
}