Make Agent Defeat Agent: Automatic Detection of Taint-Style Vulnerabilities in LLM-based Agents

Name: Make Agent Defeat Agent: Automatic Detection of Taint-Style Vulnerabilities in LLM-based Agents
Duration: 15 min
Description: Talk from 34th USENIX Security Symposium (USENIX Security '25).

Fengyu Liu

34th USENIX Security Symposium (USENIX Security '25) · Day 2 · LLM Security 3