5 papers
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…
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…
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…
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…
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…