8 papers
What Guides the Agent? Adjudicating Unauthorized Behavior via Localizing Behavior-Guiding Instructions
Yichao Gao, Yumo Zhang, Yunhao Yao +4
LLM agents integrated with external resources gain complex task capabilities, yet the unified natural-language context channel makes them vulnerable to injection attacks: untrusted…
MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP
Ruiqi Li, Zhiqiang Wang, Yunhao Yao +1
To standardize interactions between LLM-based agents and their environments, the Model Context Protocol (MCP) was proposed and has since been widely adopted. However, integrating e…
IntentMiner: Intent Inversion Attack via Tool Call Analysis in the Model Context Protocol
Yunhao Yao, Zhiqiang Wang, Haoran Cheng +3
The evolution of Large Language Models (LLMs) into Agentic AI has established the Model Context Protocol (MCP) as the standard for connecting reasoning engines with external tools.…
SoK: Trust-Authorization Mismatch in LLM Agent Interactions
Guanquan Shi, Haohua Du, Zhiqiang Wang +4
Large Language Models (LLMs) are evolving into autonomous agents capable of executing complex workflows via standardized protocols (e.g., MCP). However, this paradigm shifts contro…
Towards Deterministic Sub-0.5 us Response on Linux through Interrupt Isolation
Zhouyi Zhou, Zhili Liu, Shancong Zhang +6
Real-time responsiveness in Linux is often constrained by interrupt contention and timer handling overhead, making it challenging to achieve sub-microsecond latency. This work intr…
MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers
Zhiqiang Wang, Yichao Gao, Yanting Wang +6
By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a cornerstone of the modern autonomous ag…