Zihang Xiang

According to our database, Zihang Xiang authored at least 14 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2025

FlashDP: Private Training Large Language Models with Efficient DP-SGD.

Liangyu Wang, Junxiao Wang, Jie Ren, Zihang Xiang, David E. Keyes, Di Wang

CoRR, July, 2025

Differentially Private Sparse Linear Regression with Heavy-tailed Responses.

Xizhi Tian, Meng Ding, Touming Tao, Zihang Xiang, Di Wang

CoRR, June, 2025

Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness.

Cheng-Long Wang, Qi Li, Zihang Xiang, Yinzhi Cao, Di Wang

CoRR, June, 2025

Towards User-level Private Reinforcement Learning with Human Feedback.

Jiaming Zhang, Mingxi Lei, Meng Ding, Mengdi Li, Zihang Xiang, Difei Xu, Jinhui Xu, Di Wang

CoRR, February, 2025

Privacy Audit as Bits Transmission: (Im)possibilities for Audit by One Run.

Zihang Xiang, Tianhao Wang, Di Wang

CoRR, January, 2025

Improved Rates of Differentially Private Nonconvex-Strongly-Concave Minimax Optimization.

Ruijia Zhang, Mingxi Lei, Meng Ding, Zihang Xiang, Jinhui Xu, Di Wang

Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024

Nearly Optimal Rates of Privacy-Preserving Sparse Generalized Eigenvalue Problem.

Lijie Hu, Zihang Xiang, Jiabin Liu, Di Wang

IEEE Trans. Knowl. Data Eng., 2024

Has Approximate Machine Unlearning been evaluated properly? From Auditing to Side Effects.

Cheng-Long Wang, Qi Li, Zihang Xiang, Di Wang

CoRR, 2024

How Does Selection Leak Privacy: Revisiting Private Selection and Improved Results for Hyper-parameter Tuning.

Zihang Xiang, Cheng-Long Wang, Di Wang

CoRR, 2024

Preserving Node-level Privacy in Graph Neural Networks.

Zihang Xiang, Tianhao Wang, Di Wang

Proceedings of the IEEE Symposium on Security and Privacy, 2024

2023

Practical Differentially Private and Byzantine-resilient Federated Learning.

Zihang Xiang, Tianhao Wang, Wanyu Lin, Di Wang

Proc. ACM Manag. Data, 2023

Differentially Private Non-convex Learning for Multi-layer Neural Networks.

Hanpu Shen, Cheng-Long Wang, Zihang Xiang, Yiming Ying, Di Wang

CoRR, 2023

A Theory to Instruct Differentially-Private Learning via Clipping Bias Reduction.

Hanshen Xiao, Zihang Xiang, Di Wang, Srinivas Devadas

Proceedings of the 44th IEEE Symposium on Security and Privacy, 2023

Privacy-preserving Sparse Generalized Eigenvalue Problem.

Lijie Hu, Zihang Xiang, Jiabin Liu, Di Wang

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023