Xudong Pan
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces Tree structured Injection for Payloads (TIP), a novel black-box attack framework that reliably generates stealthy injection payloads to seize control of LLM agents utilizing the Model Context Protocol (MCP), even when defenses are present.
The paper introduces CyberEvolver, a self-evolving agent framework that iteratively revises its own operational scaffold based on failed execution attempts, significantly improving cybersecurity agent performance across various tasks.
AgentGuard is an attribute-based access control framework designed to mitigate severe security risks, such as privacy leakage and system compromise, in tool-using LLM-based agents.
Papers
AgentGuard: An Attribute-Based Access Control Framework for Tool-Use LLM-Based Agent
Jiaqi Luo, Songyang Peng, Jiarun Dai, Zhile Chen +5 more
AgentGuard is an attribute-based access control framework designed to mitigate severe security risks, such as privacy leakage and system compromise, in tool-using LLM-based agents.