activity
20242026
collaborators

5 papers

cs.CR2026

SynChain: Inducing Computer-Use Agent Systems to Construct Their Own Attack Chains

Fuyao Zhang, Jiaming Zhang, Che Wang +7

Computer-use agents~(CUAs) have transformed large language models into persistent execution systems capable of generating, storing, and reusing artifacts like skills and memory ent…

cs.CV2026

MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models

Xiongtao Sun, Hui Li, Jiaming Zhang +5

Modern Vision-Language Models (VLMs) pose significant individual-level privacy risks by linking fragmented multimodal data to identifiable individuals through hierarchical chain-of…

cs.CR2025

DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents

Fuyao Zhang, Jiaming Zhang, Che Wang +6

The reliance of mobile GUI agents on Multimodal Large Language Models (MLLMs) introduces a severe privacy vulnerability: screenshots containing Personally Identifiable Information…

cs.CR2024

DePrompt: Desensitization and Evaluation of Personal Identifiable Information in Large Language Model Prompts

Xiongtao Sun, Gan Liu, Zhipeng He +2

Prompt serves as a crucial link in interacting with large language models (LLMs), widely impacting the accuracy and interpretability of model outputs. However, acquiring accurate a…

cs.CL2024

Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles

Xiongtao Sun, Deyue Zhang, Dongdong Yang +2

Large language models (LLMs) have significantly enhanced the performance of numerous applications, from intelligent conversations to text generation. However, their inherent securi…