Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System
Published in ACL 2025, 2025
Recommended citation: Ziyou Jiang, Mingyang Li, Guowei Yang, Junjie Wang, Yuekai Huang, Zhiyuan Chang, Qing Wang: Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System. CoRR abs/2502.11358. (2025). https://doi.org/10.48550/arXiv.2502.11358
The AutoCMD approach for analyzing the information theft attack in LLM tool-learning systems, through the command injection.
Recommended citation: Ziyou Jiang, Mingyang Li, Guowei Yang, Junjie Wang, Yuekai Huang, Zhiyuan Chang, Qing Wang: Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System. CoRR abs/2502.11358. (2025).