|
I am a 4th-year Ph.D. student at King Abdullah University of Science and Technology (KAUST), advised by Di Wang. I also work with Tianhao Wang at University of Virginia. I received my Bachelor's degree in Electrical Engineering at Shanghai Jiao Tong University (SJTU) IEEE Pilot Class . I also received my Master's degree from SJTU and I worked on power electronics (specialized in hardware design and control theory) during that time. My current research is on data privacy (specifically, differential privacy) in broad machine learning applications. I am interested in making differential privacy usable and exploring its maximal potential in various applications such as federated learning, graph neural networks, and privacy audit. |
|
Publications (= means co-first author )
|
Preserving Node-level Privacy in Graph Neural Networks
Zihang Xiang, 45th IEEE Symposium on Security and Privacy (IEEE S&P 2024, Oakland), to appear [PDF] [GitHub] |
|
A Theory to Instruct Differentially-Private Learning via Clipping Bias Reduction
44th IEEE Symposium on Security and Privacy (IEEE S&P 2023, Oakland) [PDF] [GitHub] |
|
Practical Differentially Private and Byzantine-resilient Federated Learning
Zihang Xiang, International Conference on Management of Data (SIGMOD), 2023 [PDF] [GitHub] |
|
Privacy-preserving Sparse Generalized Eigenvalue Problem
Lijie Hu=, Zihang Xiang=, Jiabin Liu, The 26th International Conference on Artificial Intelligence and Statistics (AISTATS), 2023 [PDF] |
Teaching
| TA of CS229: Machine Learning, KAUST |
| TA of BioE394E: Deep Learning for Bioengineering, KAUST |
Service
| (Sub)-Reviewer: CCS2024, NDSS2023, CCS2023, PETS2023, ICML2023, IEEE-TNNLS |