Zihang Xiang

I am a 4th-year Ph.D. student at King Abdullah University of Science and Technology (KAUST), advised by Di Wang. I also work closely with Tianhao Wang at University of Virginia. I earned my Bachelor's and Master's degree in Electrical Engineering at Shanghai Jiao Tong University (SJTU) IEEE Pilot Class . I worked on power electronics (specialized in hardware design and control theory) during that time.

I will be joining Prof. Yuan Tian's group as a postdoc at UCLA in 2025's summer.

My current research is on data privacy (specifically, differential privacy). I am interested in pushing the boundaries of differential privacy via principled approaches in various applications.

Email  /  Google Scholar

profile photo

Publications [= means equal contribution ]


Preprint
Revisiting Differentially Private Hyper-parameter Tuning
Zihang Xiang, Tianhao Wang, Chenglong Wang, Di Wang
USENIX Sec'25
Privacy Audit as Bits Transmission: (Im)possibilities for Audit by One Run
Zihang Xiang, Tianhao Wang, Di Wang
34th USENIX Security Symposium
S&P'24
Preserving Node-level Privacy in Graph Neural Networks
Zihang Xiang, Tianhao Wang, Di Wang
45th IEEE Symposium on Security and Privacy
CSAW'24 Applied Research Competition Finalist
Science Advances
A privacy-preserving federated machine learning method protects patients' privacy in omic data
Juexiao Zhou, Siyuan Chen, Yulian Wu, ..., Zihang Xiang, ..., Di Wang, Xin Gao
Science Advances, VOLUME 10, ISSUE 5, 2 FEB 2024
S&P'23
A Theory to Instruct Differentially-Private Learning via Clipping Bias Reduction
44th IEEE Symposium on Security and Privacy
SIGMOD'23
Practical Differentially Private and Byzantine-resilient Federated Learning
Zihang Xiang, Tianhao Wang, Wanyu Lin, Di Wang
International Conference on Management of Data, 2023
AISTATS'23
Privacy-preserving Sparse Generalized Eigenvalue Problem
Lijie Hu=, Zihang Xiang=, Jiabin Liu, Di Wang
The 26th International Conference on Artificial Intelligence and Statistics
TKDE'23
Nearly Optimal Rates of Privacy-preserving Sparse Generalized Eigenvalue Problem
Lijie Hu=, Zihang Xiang=, Jiabin Liu, Di Wang
IEEE Transactions on Knowledge and Data Engineering, 2023

Teaching


TA of CS229: Machine Learning, KAUST
TA of BioE394E: Deep Learning for Bioengineering, KAUST
TA of CS325: Private Data Analysis, KAUST
TA of CS294: Trustworthy Machine Learning, KAUST

Service


(Sub)-Reviewer: AISTATS'2025, CCS'(2024,2023), NDSS'2023, PETS'2023, ICML'2023, IEEE-TNNLS