activity
20242026
collaborators

5 papers

cs.CR2026

LLM agents security duality: a comprehensive survey of self-security and empowered cybersecurity

Yiwei Xu, Yong Zhuang, Xuanming Liu +6

Large language model (LLM) agents are rapidly being integrated into real-world systems. Their autonomy and tool-use capabilities generate substantial value while simultaneously exp…

cs.CV2026

Light-WAM: Efficient World Action Models with State-Fusion Action Decoding

Ziang Li, Dongzhou Cheng, Yibin Wang +5

World Action Models (WAMs) extend robot policy learning by incorporating future prediction as an additional training objective, encouraging the policy to encode task-relevant tempo…

cs.CR2026

AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification

Tian Zhang, Yiwei Xu, Juan Wang +8

Large language model (LLM) agents increasingly rely on external tools and retrieval systems to autonomously complete complex tasks. However, this design exposes agents to indirect…

cs.CR2025

From Head to Tail: Efficient Black-box Model Inversion Attack via Long-tailed Learning

Ziang Li, Hongguang Zhang, Juan Wang +6

Model Inversion Attacks (MIAs) aim to reconstruct private training data from models, leading to privacy leakage, particularly in facial recognition systems. Although many studies h…

cs.CR2024

A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learning

Xiaoyang Xu, Mengda Yang, Wenzhe Yi +5

Split Learning (SL) is a distributed learning framework renowned for its privacy-preserving features and minimal computational requirements. Previous research consistently highligh…