I am a research fellow at the School of Computing Technologies, RMIT University, Australia, advised by Prof. Xun Yi. Before that, I obtained my Ph.D. degree from Monash University, jointly advised by Assoc. Prof. Xingliang Yuan and Prof. Shirui Pan. Prior to pursuing my Ph.D., I obtained a Bachelor’s degree in Mathematics and Applied Mathematics from Nanjing University of Science and Technology (NJUST), and a Master’s degree in Computer Science and Technology from Institute of Computing Technology, Chinese Academy of Sciences (ICT, CAS).
I have broad interests in the development of Trustworthy Machine Learning Systems, including (1) individual trustworthiness aspects such as robustness, explainability, privacy, and fairness; (2) the intricate interplay among them, such as the trade-offs between fairness and privacy. If you are interested in these topics, please feel free to contact me.
05/2025: One paper "BiMark: Unbiased Multilayer Watermarking for Large Language Models" has been accepted to ICML 2025!
01/2025: One paper "Dynamic Graph Unlearning: A General and Efficient Post-Processing Method via Gradient Transformation" has been accepted to WWW 2025!
03/2024: One paper "Unraveling Privacy Risks of Individual Fairness in Graph Neural Networks" has been accepted to ICDE 2024!
Unraveling Privacy Risks of Individual Fairness in Graph Neural Networks.
He Zhang, Xingliang Yuan, Shirui Pan.
IEEE International Conference on Data Engineering (ICDE), 2024. (CORE A*, Acceptance rate 22.75%)
Trustworthy Graph Neural Networks: Aspects, Methods, and Trends.
He Zhang, Bang Wu, Xingliang Yuan, Shirui Pan, Hanghang Tong, Jian Pei.
Proceedings of the IEEE, 2024. (CCF A, SJR Q1, Impact factor 25.9, Featured as Issue cover)
GraphGuard: Detecting and Counteracting Training Data Misuse in Graph Neural Networks.
Bang Wu, He Zhang, Xiangwen Yang, Shuo Wang, Minhui Xue, Shirui Pan, Xingliang Yuan.
The Network and Distributed System Security Symposium (NDSS), 2024. (CORE A*, Acceptance rate 15.0%)