About
Hi there, welcome to my homepage! My name is Qiming Zhang, currently an undergraduate research intern at Johns Hopkins University & University of Georgia. I am honored to conduct my research under the guidance of Professor Chaowei Xiao & Professor Zhen Xiang. My research interests are in AI safety, with a focus on privacy and security in AI, including securing agentic LLMs against multimodal privacy leakage and OS-level risks of computer-use agents, and, more recently, understanding how agent memory shapes LLM reasoning on long horizon tasks.
Previously, I obtained my B.S. in Computer Science from 
University of Wisconsin-Madison.
I am always open to collaboration and the exchange of ideas. If you'd like to discuss potential research opportunities or simply connect, please feel free to reach out to me at qzhang478@wisc.edu.
📢 I am actively seeking PhD opportunities for Fall 2026!
Education
Selected Publications
View All →
Code Agent can be an End-to-end System Hacker: Benchmarking Real-world Threats of Computer-use Agent
Weidi Luo, Qiming Zhang, Tianyu Lu, Xiaogeng Liu, Bin Hu, Hung-Chun Chiu, Siyuan Ma, Yizhe Zhang, Xusheng Xiao, Yinzhi Cao, Zhen Xiang, Chaowei Xiao
Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models
Weidi Luo†, Qiming Zhang†, Tianyu Lu†, Xiaogeng Liu, Bin Hu, Yue Zhao, Jieyu Zhao, Song Gao, Patrick McDaniel, Zhen Xiang, Chaowei Xiao
Service
Peer Review: ACL Rolling Review (ARR) Emergency Reviewer (May & July 2025)