Publications

You can also find my articles on my Google Scholar profile.

Changyue Jiang, Wenqi Zhang, Xudong Pan, Geng Hong, Min Yang

ICML 2026 2026

This work improves behavioral safety for LLM agents by correcting risky thoughts before action execution.

Changyue Jiang, Jiayi Wang, Xin Wen, Jiarun Dai, Geng Hong, Xudong Pan

USENIX Security 2026 2026

MATE is a policy-aware security auditing framework for mobile agents, using synthesis-driven trajectory learning to find unsafe behaviors.

Wenqi Zhang, Yulin Shen, Changyue Jiang, Jiarun Dai, Geng Hong, Xudong Pan

ACM CCS 2026 2026

MirrorGuard improves the security of computer-use agents by using simulation-to-real reasoning correction.

Changyue Jiang, Xudong Pan, Geng Hong, Chenfu Bao, Yang Chen, Min Yang

arXiv preprint 2024

This work studies knowledge-base extraction attacks against retrieval-augmented LLM applications and introduces a feedback-guided extraction method.