📖 Publications

(✉️ is the corresponding author)

Preprint

• [Preprint] IDDM: Identity-Decoupled Personalized Diffusion Models with a Tunable Privacy-Utility Trade-off
  Linyan Dai, Xinwei Zhang, Haoyang Li, Qingqing Ye, Haibo Hu
  Arxiv, 2026.
  

• [Preprint] Grounding-Driven Attack: Improving Encoder-based Adversarial Transferability against Large Vision-Language Models
  Xinwei Zhang, Li Bai, Tianwei Zhang, Youqian Zhang, Qingqing Ye, Yingnan Zhao, Ruochen Du, Haibo Hu
  Arxiv, 2026.
  

2026

• [ICML’26] On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
  Xinwei Zhang, Hangcheng Liu, Li Bai✉️, Hao Wang, Qingqing Ye, Tianwei Zhang, Haibo Hu
  In Proc. of International Conference on Machine Learning, 2026.
  [Code] [PDF]

• [USENIX SEC’26] United We Defend: Collaborative Membership Inference Defenses in Federated Learning
  Li Bai, Junxu Liu, Sen Zhang, Xinwei Zhang, Qingqing Ye, Haibo Hu✉️
  In Proc. of USENIX Security Symposium, 2026.
  [Code] [PDF]

• [TDSC’26] A Deep Dynamic Graph Generative Framework for Blockchain Phishing Detection
  Siyi Xiao, Lejun Zhang✉️ , Xinwei Zhang, Sen Zhang, Shen Su, Jing Qiu, Ran Guo, Haibo Hu
  IEEE Transactions on Dependable and Secure Computing (TDSC), 2026.
  [PDF]

2025

• [WWW’25] MER-Inspector: Assessing Model Extraction Risks from An Attack-Agnostic Perspective
  Xinwei Zhang, Haibo Hu✉️ , Qingqing Ye, Li Bai, Huadi Zheng
  In Proc. of The ACM Web Conference (WWW), 2025.
  [Code] [PDF]

• [NeurIPS’25] Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
  Li Bai, Qingqing Ye, Xinwei Zhang, Sen Zhang, Zi Liang, Jianliang Xu, Haibo Hu✉️
  In Proc. Neural Information Processing Systems (NeurIPS), December, 2025.
  [Code] [PDF]

• [TIFS’25] ProVFL: Property Inference Attacks against Vertical Federated Learning
  Li Bai, Xinwei Zhang, Sen Zhang, Qingqing Ye, Haibo Hu✉️
  IEEE Transactions on Information Forensics and Security (TIFS), vol. 20, pp. 6529-6543, 2025.
  [Code] [PDF]

2024 and Before

• [TVT’24] Enabling Deep Learning-based Physical-layer Secret Key Generation for FDD-OFDM Systems in Multi-Environments
  Xinwei Zhang, Guyue Li✉️ , Junqing Zhang, Linning Peng, Aiqun Hu, Xianbin Wang
  IEEE Transactions on Vehicular Technology (TVT), vol. 73, no. 7, pp. 10135-10149, July 2024.

• [ICC’24] A Secure and Reliable Blockchain-based Audit Log System
  Zhonghao Liu, Xinwei Zhang, Guyue Li, Helei Cui, Jiaheng Wang, Bin Xiao✉️
  In Proc. IEEE International Conference on Communications (ICC), 2024.

• [ICC’23] DBE-voting: A Privacy-preserving and Auditable Blockchain-based E-voting System
  Zhonghao Liu, Xinwei Zhang, Laphou Lao, Guyue Li, Bin Xiao✉️
  In Proc. IEEE International Conference on Communications (ICC), 2023.

• [IoT-J’22] Deep Learning-based Physical-Layer Secret Key Generation for FDD Systems
  Xinwei Zhang, Guyue Li✉️ , Junqing Zhang, Aiqun Hu, Zongyue Hou, Bin Xiao
  IEEE Internet of Things Journal (IoT-J), vol. 9, no. 8, pp. 6081-6094, April 2022.
  [Code]

• [VTC’21] Secret Key Generation for FDD Systems Based on Complex-Valued Neural Network
  Xinwei Zhang, Guyue Li✉️ , Zongyue Hou and Aiqun Hu
  In Proc. 2021 IEEE 94th Vehicular Technology Conference (VTC), 2021.

• [INFOCOM-W’21] Secret Key Generation Scheme Based on Generative Adversarial Networks in FDD Systems
  Zongyue Hou and Xinwei Zhang ✉️
  In Proc. IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), 2021.

Other Publications

• [China Patent] 李古月；张鑫伟；侯宗越；王星宇，一种基于深度学习的频分双工系统密钥生成方法，已授权，2022/11/18，CN112906035B.