Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents

arXiv:2402.11208v1 Announce Type: cross
Abstract: Leveraging the rapid development of Large Language Models LLMs, LLM-based agents have been developed to handle various real-world applications, including finance, healthcare, and shopping, etc. It is crucial to ensure the reliability and security of LLM-based agents during applications. However, the safety issues of LLM-based agents are currently under-explored. In this work, we take the first step to investigate one of the typical safety threats, backdoor attack, to LLM-based agents. We first formulate a general …

abstract agents applications arxiv backdoor cs.ai cs.cl cs.cr development etc finance healthcare language language models large language large language models llm llms reliability safety security shopping threats type world