Li Bai

Associate Professor, School of Cyber Science and Engineering, Southeast University

Email: libai [at] seu [dot] edu [dot] cn

Biography

I am an Associate Professor at Southeast University, China. I received my Ph.D. degree in January 2026 under the supervision of Prof. Haibo Hu and subsequently worked as a Postdoctoral Fellow in the ASTAPLE Lab at The Hong Kong Polytechnic University.

My research interests include trustworthy machine learning and AI security, with a primary focus on privacy and security attacks against modern machine learning systems.

Academic Services

Journal Reviewer

  • IEEE Transactions on Dependable and Secure Computing (TDSC)
  • IEEE Transactions on Information Forensics and Security (TIFS)

Conference Reviewer

  • Conference on Neural Information Processing Systems (NeurIPS)
  • Annual Meeting of the Association for Computational Linguistics (ACL)

Publications

See the complete publication list on the DBLP page.

Journal Papers

  1. Li Bai, Xinwei Zhang, Sen Zhang, Qingqing Ye, and Haibo Hu.
    “ProVFL: Property inference attacks against vertical federated learning.”
    IEEE Transactions on Information Forensics and Security (TIFS), 2025.

  2. Li Bai, Haibo Hu, Qingqing Ye, Jianliang Xu, Jin Li, Chengfang Fang, and Jie Shi.
    “RMR: A relative membership risk measure for machine learning models.”
    IEEE Transactions on Dependable and Secure Computing (TDSC), 2025.

  3. Zhu Jiang, Haibo Hu, Qingqing Ye, and Li Bai.
    “Auditing MLaaS Inference Service Quality without Ground Truth via Mutual Information.”
    IEEE Transactions on Information Forensics and Security (TIFS), 2025.

  4. Li Bai, Haibo Hu, Qingqing Ye, Haoyang Li, Leixia Wang, and Jianliang Xu.
    “Membership inference attacks and defenses in federated learning: A survey.”
    ACM Computing Surveys, 2024.

Conference Papers

  1. Xinwei Zhang, Hangcheng Liu, Li Bai, Hao Wang, Qingqing Ye, Tianwei Zhang, and Haibo Hu. (Corresponding Author)
    “On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression.”
    ICML, 2026.

  2. Li Bai, Junxu Liu, Sen Zhang, Xinwei Zhang, Qingqing Ye, and Haibo Hu.
    “United We Defend: Collaborative Membership Inference Defenses in Federated Learning.”
    USENIX Security, 2026.

  3. Li Bai, Qingqing Ye, Xinwei Zhang, Sen Zhang, Zi Liang, Jianliang Xu, and Haibo Hu.
    “Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts.”
    NeurIPS, 2025.

  4. Xinwei Zhang, Haibo Hu, Qingqing Ye, Li Bai, and Huadi Zheng.
    “MER-Inspector: Assessing model extraction risks from an attack-agnostic perspective.”
    WWW, 2025.

  5. Haoyang Li, Li Bai, Qingqing Ye, Haibo Hu, Yaxin Xiao, Huadi Zheng, and Jianliang Xu.
    “A sample-level evaluation and generative framework for model inversion attacks.”
    AAAI, 2025.