- haodi.wang@cityu.edu.hk
- Google Scholar
- GitHub
- Kowloon, Hong Kong SAR
City University of Hong Kong
Haodi Wang
Research Assistant Professor, Department of Computer Science
I am a Research Assistant Professor in the Department of Computer Science at City University of Hong Kong, advised by Prof. Xiaohua Jia. My research focuses on zero-knowledge proofs, verifiable computation, privacy-preserving machine learning, and trustworthy AI.
I received my Ph.D. and B.Sc. from Beijing Normal University. I was a visiting Ph.D. student at Virginia Tech, advised by Prof. Thang Hoang. Before joining CityU, I was a Postdoctoral Research Fellow at the Laboratory for AI-Powered Financial Technologies in Hong Kong.
Research Interests
My work sits at the intersection of applied cryptography and secure AI systems, with an emphasis on making machine learning workflows verifiable, privacy-preserving, and deployable.
Appointments
-
08/2025 - Present
Research Assistant Professor
Department of Computer Science, City University of Hong Kong. -
06/2024 - 08/2025
Postdoctoral Research Fellow
Laboratory for AI-Powered Financial Technologies, Hong Kong Science Park.
Recent News
- 2026 Two papers accepted to IJCNN 2026 and DASFAA 2026.
- 2025 "Zero-Knowledge AI Inference with High Precision" accepted to ACM CCS 2025.
- 2025 "Accelerating Zero-Shot NAS with Feature Map-Based Proxy and Operation Scoring Function" accepted by TPAMI.
- 08/2025 Joined City University of Hong Kong as a Research Assistant Professor.
- 06/2024 Completed the Ph.D. degree at Beijing Normal University.
Selected Publications
- C3 Zero-Knowledge AI Inference with High Precision. A. Riasi, H. Wang, R. Behnia, V. Vo, T. Hoang. ACM CCS, 2025.
- J1 Accelerating Zero-Shot NAS with Feature Map-Based Proxy and Operation Scoring Function. T. Jiang, H. Wang, R. Bie, C. Yuan. IEEE TPAMI, 2025.
- C6 Label Noise Correction for Federated Learning: A Secure, Efficient and Reliable Realization. H. Wang, T. Jiang, Y. Guo, F. Guo, R. Bie, X. Jia. IEEE ICDE, 2024.
- C8 MeCo: Zero-Shot NAS with One Data and Single Forward Pass via Minimum Eigenvalue of Correlation. T. Jiang*, H. Wang*, R. Bie. NeurIPS Spotlight, 2023.