collaborators

5 papers

cs.CR2026

Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies

Ruixiao Lin, Xinhao Deng, Qingming Li +12

Self-evolving LLM agent systems, which autonomously update their model parameters, memory, tools, and architectures, introduce a qualitatively new threat landscape in which adversa…

cs.AI2026

DART: Semantic Recoverability for Structured Tool Agents

Ke Yang, Panpan Li, Zonghan Wu +3

When a structured tool agent fails mid-execution, the runtime faces a dilemma: replaying the entire task is safe but wasteful, while restoring from a local checkpoint is efficient…

cs.CR2025

Beyond a Single Perspective: Towards a Realistic Evaluation of Website Fingerprinting Attacks

Xinhao Deng, Jingyou Chen, Linxiao Yu +6

Website Fingerprinting (WF) attacks exploit patterns in encrypted traffic to infer the websites visited by users, posing a serious threat to anonymous communication systems. Althou…

cs.CR2025

Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions

Yixiang Zhang, Xinhao Deng, Zhongyi Gu +4

Large Language Models (LLMs) are increasingly deployed as agents that orchestrate tasks and integrate external tools to execute complex workflows. We demonstrate that these interac…

cs.CR2025

Towards Robust Multi-tab Website Fingerprinting

Xinhao Deng, Xiyuan Zhao, Qilei Yin +5

Website fingerprinting enables an eavesdropper to determine which websites a user is visiting over an encrypted connection. State-of-the-art website fingerprinting (WF) attacks hav…