I am currently studying at the College of Software, Zhejiang University, under the supervision of Meng Han.

My research focuses on AI Security, specifically Model Watermarking and Fingerprinting, involving LLM and VLM. ๐Ÿ“š๐Ÿ” If you are interested in this topic, feel free to contact me via email! โœ‰๏ธ

๐Ÿ”ฅ News

๐Ÿš€ Projects

  • Awesome LLM Copyright Protection - A curated collection of research and techniques for protecting intellectual property of large language models, including watermarking, fingerprinting, and more. [Website]

๐Ÿ“ Publications

Conference Papers

ACL 2025 Main
sym

MEraser: An Effective Fingerprint Erasure Approach for Large Language Models

Jingxuan Zhang and Zhenhua Xu (co-first authors), Rui Hu, Wenpeng Xing, Xuhong Zhang, Meng Han Code

LLMs are widely used, raising concerns about model ownership. MEraser is a method to remove backdoor-based fingerprints from LLMs while preserving performance. It uses a two-phase fine-tuning strategy with mismatched and clean datasets, achieving fingerprint removal with minimal data. The method is transferable across models without repeated training, highlighting vulnerabilities in current techniques and setting benchmarks for better model protection.

Journal Papers

None yet.

Preprints

๐Ÿ’ป Internships

๐Ÿ“– Educations

  • 2024.06 - Present, Masterโ€™s student in Software Engineering, College of Software, Zhejiang University
  • 2020.09 - 2024.06, Bachelorโ€™s degree in Digital Media Technology, College of Computer Science and Technology, College of Software, Zhejiang University of Technology