About Me
(in about 448 words)
Intro
Hi! My Chinese name is Zhiyuan Li (ζεΏθΏ), and my English name is Zane Lee. I am currently a PhD candidate at the University of Chinese Academy of Sciences (UCAS) and the Institute of Software, Chinese Academy of Science (ISCAS) under the supervision of Prof. Jingzheng Wu and Associate Prof. Xiang Ling. I obtained my Bachelor's degree from School of Artificial Intelligence at Xidian University in 2022.
My research interests include AI systems security. Besides, I am also exploring how to use insights from software to improve the robustness of hardware. My current work focuses on the security of deep learning libraries/compilers.
Research Interests
- Security of AI Systems
- Security of DL libraries/compilers, LLM safety (language models and multi-modal models)
- Fuzz Testing
- Fuzzing for everything (software and hardware), Fuzzing with LLMs
News
Jun 27, 2026π Our research paper "Confused Deputy Attack Against Model Context Protocol" was accepted by TOSEM.
Nov 8, 2025π Our research paper "Similarity-guided Block-level Mutation for RISC-V Processor Fuzzing" was accepted by DATE 2026. Congrats to Hao.
Nov 8, 2025π Our research paper "VFCionX: Bridging Large and Small Models for Robust Vulnerability-Fixing Commit Identification" was accepted by AAAI 2026. Congrats to Xing.
Sep 16, 2025π Hass Lab won the 1st place at HACK@CHES 2025.
Selected Publications
- [TOSEM'26] Confused Deputy Attack Against Model Context Protocol
Zhiyuan Li, Jingzheng Wu, Yuhao Peng, Tianyue Luo, Xing Cui, Xiang Ling
ACM Transactions on Software Engineering and Methodology (TOSEM) - [ICSE'25] The Seeds of the FUTURE Sprout from History: Fuzzing for Unveiling Vulnerabilities in Prospective Deep Learning Libraries
Zhiyuan Li, Jingzheng Wu, Xiang Ling, Tianyue Luo, Zhiqing Rui, Yanjun Wu
In Proceedings of the 47th ACM SIGSOFT International Conference on Software Engineering, Ottawa, Canadaπ ACM SIGSOFT Distinguished Paper Award
Service
- Program Committee/Reviewer
- Conference: AAAI 2026, AAAI 2027
- Journal: TOSEM, TSE
