Lijin Wang

Zhejiang University wanglijin@zju.edu.cn

prof_pic.jpg

📍 Hangzhou, China

I am currently a Research Assistant at Hong Kong University of Science and Technology (Guangzhou), under the supervision of Prof. Xinlei He.

Before that, I obtained my Master’s degree at Zhejiang University under the supervision of Prof. Ziqi Yang, and my Bachelor’s degree at Hangzhou City University under the supervision of Prof. Jinling Wei.

My research interest lies in Trustworthy AI. Currently, I am dedicated to exploring how potential security issues arise in ML models. Ultimately, I seek to understand why these security issues occur, aiming to develop a unified theory to explain the security vulnerabilities in ML models.

news

Jul 28, 2025 👨‍💻 I will serve as a reviewer for AAAI 2026.
Jan 25, 2025 🎉 One paper got accepted by USENIX Security 2025.
Sep 30, 2024 👨‍💻 I will serve as a reviewer for ICLR 2025.
Mar 30, 2024 🎓 I graduated with a Master’s degree from Zhejiang University.
Mar 05, 2024 🎉 One paper got accepted by USENIX Security 2024.

selected publications

  1. mergebackdoor.png
    From Purity to Peril: Backdooring Merged Models From “Harmless” Benign Components
    Lijin Wang, Jingjing Wang , Tianshuo Cong , and 3 more authors
    In 34th USENIX Security Symposium (USENIX Security 25) , Jan 2025
  2. PEI.png
    Property Existence Inference against Generative Models
    Lijin Wang, Jingjing Wang , Jie Wan , and 3 more authors
    In 33rd USENIX Security Symposium (USENIX Security 24) , Aug 2024
  3. BA.png
    BounceAttack: A Query-Efficient Decision-based Adversarial Attack by Bouncing into the Wild
    Jie Wan , Jianhao Fu , Lijin Wang, and 1 more author
    In 2024 IEEE Symposium on Security and Privacy (SP) , May 2024
  4. purifier.png
    Purifier: Defending data inference attacks via transforming confidence scores
    Ziqi Yang(advisor) , Lijin Wang, Da Yang , and 5 more authors
    In Proceedings of the AAAI Conference on Artificial Intelligence (oral) , Jun 2023