4 papers · 1 filter
What's in Your Agent's Context? Context Privilege Escalation Attacks against AI Agent Harness
Zichuan Li, Jian Cui, Ashley Chen +2
Real-world, high-profile AI agent harnesses often rely on vendor-proprietary or opaque designs for context assembly, leaving the sources and underlying logic of assembled context p…
Agent Data Injection Attacks are Realistic Threats to AI Agents
Woohyuk Choi, Juhee Kim, Taehyun Kang +3
AI agents act on behalf of user prompts, consuming external data and taking actions based on the agent context. Prior research on AI agent security has primarily focused on indirec…
Maris: A Formally Verifiable Privacy Policy Enforcement Paradigm for Multi-Agent Collaboration Systems
Jian Cui, Zichuan Li, Chi Wang +2
Multi-agent collaboration systems (MACS), powered by large language models (LLMs), solve complex problems efficiently by leveraging each agent's specialization and communication be…
Les Dissonances: Cross-Tool Harvesting and Polluting in Pool-of-Tools Empowered LLM Agents
Zichuan Li, Jian Cui, Xiaojing Liao +1
Large Language Model (LLM) agents are autonomous systems powered by LLMs, capable of reasoning and planning to solve problems by leveraging a set of tools. However, the integration…