Rui Zhang

Postdoc Research Fellow
The University of Hong Kong
Office: P207, Graduate House, HKU

About

I am a Postdoc Research Fellow at the HKU Musketeers Foundation Institute of Data Science (IDS), The University of Hong Kong (HKU), working with Prof. Ho Chen. Before that, I obtained my Ph.D. in Computer Science from The Hong Kong Polytechnic University (PolyU). My research interests include AI security & privacy, trustworthy machine learning, distributed learning, and LLM-based applications.

Please feel free to reach out if you have any questions or would like to collaborate on research projects!

News

Publications

The full list of publications is on Google Scholar.

Building Gradient Bridges: Label Leakage from Restricted Gradient Sharing in Federated Learning

Rui Zhang, Ka-Ho Chow, Ping Li

arXiv preprint, 2025

Geminio: Language-Guided Gradient Inversion Attacks in Federated Learning

Junjie Shan, Ziqi Zhao, Jialin Lu, Rui Zhang, Siu Ming Yiu, Ka-Ho Chow

International Conference on Computer Vision (ICCV), 2025

GradFilt: Class-wise Targeted Data Reconstruction from Gradients in Federated Learning

Rui Zhang, Song Guo, Ping Li

The Web Conference (WWW), 2024

Posterior Probability-based Label Recovery Attack in Federated Learning

Rui Zhang, Song Guo, Ping Li

ICLR PML Workshop, 2024

A Survey on Gradient Inversion: Attacks, Defenses and Future Directions

Rui Zhang, Song Guo, Junxiao Wang, Xin Xie, Dacheng Tao

International Joint Conference on Artificial Intelligence (IJCAI), 2022

Cycle: Sustainable Off-Chain Payment Channel Network with Asynchronous Rebalancing

Zicong Hong, Song Guo, Rui Zhang, Peng Li, Yunfeng Zhan, Wuhui Chen

International Conference on Dependable Systems and Networks (DSN), 2022

Building Gradient Bridges: Label Leakage from Restricted Gradient Sharing in Federated Learning

Rui Zhang, Ka-Ho Chow, Ping Li

arXiv preprint, 2025

Geminio: Language-Guided Gradient Inversion Attacks in Federated Learning

Junjie Shan, Ziqi Zhao, Jialin Lu, Rui Zhang, Siu Ming Yiu, Ka-Ho Chow

International Conference on Computer Vision (ICCV), 2025

GradFilt: Class-wise Targeted Data Reconstruction from Gradients in Federated Learning

Rui Zhang, Song Guo, Ping Li

The Web Conference (WWW), 2024

Posterior Probability-based Label Recovery Attack in Federated Learning

Rui Zhang, Song Guo, Ping Li

ICLR PML Workshop, 2024

Privacy Inference for Data Auditing

Rui Zhang, Song Guo

International Symposium on AI, Data and Digitalization (SAIDD), 2023

MGIA: Mutual Gradient Inversion Attack in MultiModal Federated Learning (Student Abstract)

Xuan Liu, Siqi Cai, Lin Li, Rui Zhang, Song Guo

AAAI Conference on Artificial Intelligence (AAAI), 2023

A Survey on Gradient Inversion: Attacks, Defenses and Future Directions

Rui Zhang, Song Guo, Junxiao Wang, Xin Xie, Dacheng Tao

International Joint Conference on Artificial Intelligence (IJCAI), 2022

Cycle: Sustainable Off-Chain Payment Channel Network with Asynchronous Rebalancing

Zicong Hong, Song Guo, Rui Zhang, Peng Li, Yunfeng Zhan, Wuhui Chen

International Conference on Dependable Systems and Networks (DSN), 2022

A Novel Pseudonym Linking Scheme for Privacy Inference in VANETs

Rui Zhang, Xin Wang, Peng Cheng, Jiming Chen.

Vehicular Technology Conference (VTC), 2020

An Industrial Control System Testbed for the Encrypted Controller

Xing Li, Mengxiang Liu, Rui Zhang, Peng Cheng, Jiming Chen

International Conference on Cyber-Physical Systems (ICCPS), 2018

A Simulation-based Platform for Privacy Preservation Research in VANETs

Peng Cheng, Rui Zhang, Linkang Du, Jiming Chen

Chinese Patent (No. CN110189517B), 2020

Experiences

Services

  • ACL (2025)
  • ICCV (2025)
  • ICLR (2025-2026)
  • AAAI (2025-2026)
  • CVPR (2024-2026)
  • IJCAI (2024-2025)
  • INFOCOM (2022-2024)
  • IEEE Transactions on Parallel and Distributed Systems (TPDS)
  • ACM Computing Surveys (CSUR)
  • Journal of Sensors
  • IEEE Access
  • AAAI (2025-2026)
  • IJCAI (2024-2025)

Teachings

Teaching Assistant at PolyU:

Acknowledgement

This webpage was built based on a template by Martin Saveski. Thanks for the author's contribution.