8 papers · 1 filter
AutoDojo: Adaptive Black-Box Attacks Reveal the Limits of IPI Defenses and Task-Specification Effects in LLM Agents
Xinhang Ma, Taoran Li, Chaowei Xiao +3
Indirect prompt injection (IPI) is a major security threat to LLM-powered agents. Thus, a growing body of work have proposed a variety of defensive approaches against IPI. These ca…
Runtime Skill Audit: Targeted Runtime Probing for Agent Skill Security
Tu Lan, Chaowei Xiao
Agent skills let LLM agents reuse instructions, resources, tools, and workflows, but they also create a new place for malicious behavior to hide. A skill may look benign in its doc…
AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?
Hao Li, Ruoyao Wen, Shanghao Shi +3
AI agents that autonomously interact with external tools and environments have shown great promise across real-world applications. However, their reliance on external data exposes…
Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models
Weidi Luo, Xiaofei Wen, Tenghao Huang +5
Large language models (LLMs) are increasingly deployed for everyday tasks, including food preparation and health-related guidance. However, food safety remains a high-stakes domain…
Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks
Chong Xiang, Drew Zagieboylo, Shaona Ghosh +5
AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigge…
AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management
Ruoyao Wen, Hao Li, Chaowei Xiao +1
Indirect prompt injection threatens LLM agents by embedding malicious instructions in external content, enabling unauthorized actions and data theft. LLM agents maintain working me…