9 papers
OBLIVION: Workflow-Level Operational Skill Unlearning for Deployed Agents
Zhengyang Shan, Xu Qian, Jiayun Xin +3
Large language model agents are becoming operational interfaces to files, memories, registries, and external tools. This deployment shift creates a new skill revocation problem: af…
Don't believe everything you read: Understanding and Measuring MCP Behavior under Misleading Tool Descriptions
Zhihao Li, Boyang Ma, Xuelong Dai +4
The Model Context Protocol (MCP) enables large language models to invoke external tools through natural-language descriptions, forming the foundation of many AI agent applications.…
"MCP Does Not Stand for Misuse Cryptography Protocol": Uncovering Cryptographic Misuse in Model Context Protocol at Scale
Biwei Yan, Yue Zhang, Minghui Xu +5
The Model Context Protocol (MCP) is rapidly emerging as the middleware for LLM-based applications, offering a standardized interface for tool integration. However, its built-in sec…
Dataset Ownership in the Era of Large Language Models
Kun Li, Cheng Wang, Minghui Xu +2
As datasets become critical assets in modern machine learning systems, ensuring robust copyright protection has emerged as an urgent challenge. Traditional legal mechanisms often f…
LIFT: Automating Symbolic Execution Optimization with Large Language Models for AI Networks
Ruoxi Wang, Kun Li, Minghui Xu +5
Dynamic Symbolic Execution (DSE) is a key technique in program analysis, widely used in software testing, vulnerability discovery, and formal verification. In distributed AI system…
We Urgently Need Privilege Management in MCP: A Measurement of API Usage in MCP Ecosystems
Zhihao Li, Kun Li, Boyang Ma +3
The Model Context Protocol (MCP) has emerged as a widely adopted mechanism for connecting large language models to external tools and resources. While MCP promises seamless extensi…