5 papers
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…
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…
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…
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…
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…