Hanshen Xiao
Assistant Professor of Computer Science
Hanshen Xiao is an Assistant Professor in the Department of Computer Science. He received his Ph.D. degree in computer science from MIT and B.S. degree in Mathematics from Tsinghua University. Before joining Purdue, he was a research scientist at NVIDIA Research. His research focuses on provable trustworthy machine learning and computation, with a particular focus on automated black-box privatization, differential trust with applications on backdoor defens… ↓More
Joined department: Fall 2025
Research Areas
- Information Security and Assurance
- Artificial Intelligence, Machine Learning, and Natural Language Processing
- Human-Computer Interaction
- Distributed Systems
- Theory of Computing, Algorithms, and Quantum Computing
Education
Ph.D., Massachusetts Institute of Technology, Computer Science (2024)
M.S. , Massachusetts Institute of Technology, Computer Science (2019)
B.S. , Tsinghua University, Mathematics (2017) (honorary)
Hanshen Xiao is an Assistant Professor in the Department of Computer Science. He received his Ph.D. degree in computer science from MIT and B.S. degree in Mathematics from Tsinghua University. Before joining Purdue, he was a research scientist at NVIDIA Research. His research focuses on provable trustworthy machine learning and computation, with a particular focus on automated black-box privatization, differential trust with applications on backdoor defense and memorization mitigation, and trustworthiness evaluation.
Selected Publications
One-Sided Bounded Noise: Theory, Optimization Algorithms and Applications, Hanshen Xiao, Jun Wan, Elaine Shi and Srini Devadas, ACM CCS (2025)
Trustworthy Machine Learning through Data-Specific Indistinguishability, Hanshen Xiao, Zhen Yang, and G. Edward Suh, ICML (2025)
Formal privacy proof of data encoding: The possibility and impossibility of learnable encryption, Hanshen Xiao, G. Edward Suh, and Srini Devadas, ACM CCS (2024)
PAC Privacy: Automatic Privacy Measurement and Control of Data Processing, Hanshen Xiao and Srini Devadas, CRYPTO (2023)
Geometry of Sensitivity: Twice Sampling and Hybrid Clipping in Differential Privacy with Optimal Gaussian Noise and Application to Deep Learning, Hanshen Xiao, Jun Wan and Srini Devadas, ACM CCS (2023)