collaborators

7 papers

cs.SE2026

When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents

Kaiyue Yang, Yuyan Bu, Jingwei Yi +5

As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant. However, prior tool-selection studies focus on saf…

cs.CR2026

When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents

Shi Liu, Xuehai Tang, Xikang Yang +4

The rise of tool-using Large Language Model (LLM) agents, standardized by protocols like the Model Context Protocol (MCP), has unlocked unprecedented autonomous execution capabilit…

cs.CR2026

RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents

Wenjie Xiao, Xuehai Tang, Biyu Zhou +2

Agent skills introduce a new and more severe form of indirect injection for LLM agents: unlike traditional indirect prompt injection, attackers can hide malicious instructions insi…

cs.CL2026

FABLE: Fine-grained Fact Anchoring for Unstructured Model Editing

Peng Wang, Biyu Zhou, Xuehai Tang +2

Unstructured model editing aims to update models with real-world text, yet existing methods often memorize text holistically without reliable fine-grained fact access. To address t…

cs.CL2025

Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs

Xikang Yang, Biyu Zhou, Xuehai Tang +2

Large Language Models (LLMs) demonstrate impressive capabilities across a wide range of tasks, yet their safety mechanisms remain susceptible to adversarial attacks that exploit co…

cs.CL2025

LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing

Peng Wang, Biyu Zhou, Xuehai Tang +2

Large Language Models often contain factually incorrect or outdated knowledge, giving rise to model editing methods for precise knowledge updates. However, current mainstream locat…