collaborators
Showing cs.CRShow all

8 papers · 1 filter

cs.CR2026

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…

cs.CR2026

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…

cs.CR2026

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…

cs.CR2026

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…

cs.CR2026

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…

cs.CR2026

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…