About
Hi there, welcome to my homepage! I am Qiming Zhang, a first-year PhD student at 
University of South Florida advised by Prof. Fengchun Qiao.
My research interests are in AI safety, security and privacy, and more recently, studying how memory system augments LLM agent's reasoning capability on long horizon tasks.
Previously, I obtained my B.S. in Computer Science from 
University of Wisconsin-Madison. I am honored to conduct research under the guidance of Prof. Chaowei Xiao and Prof. Zhen Xiang. I am also profoundly grateful for Weidi's mentorship, which has guided my engagement in cutting-edge research since March 2025.
News
🎉 One paper is accepted by 
(Findings)! Thanks to all the collaborators!
🎉 One paper is accepted by 2026! Thanks to all the collaborators!
Selected Publications
View All →
Your Harness is Not Secure: Benchmarking Real-world Threat of Command Line Interface 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
* denotes equal contribution
Oral - ICML 2026 Workshop on Agents in the Wild (Top 1.22%)
Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models
Weidi Luo*, Tianyu Lu*, Qiming Zhang*, Xiaogeng Liu, Bin Hu, Yue Zhao, Jieyu Zhao, Song Gao, Patrick McDaniel, Zhen Xiang, Chaowei Xiao
* denotes equal contribution
23,000+ views, 1,300+ shares · 机器之心 Synced
Service
Peer Review:
- Conference Reviewer of NeurIPS 2026, EMNLP 2026, COLM 2026, ECCV 2026, ACL 2026, CVPR 2026, EMNLP 2025
- Journal Reviewer of Tsinghua Science and Technology
Education
University of South Florida
08/2026 - Present
University of Wisconsin-Madison
05/2025