Ye Zheng (郑烨)

Ph.D. student in Computer Science
Rochester Institute of Technology (RIT)
Advisor: Dr. Yidan Hu

Research topics: AI Privacy, Differential Privacy, and past topics

Resume - G. Scholar - GitHub - ZhiHu

Publications (full list at G. Scholar)

See latest three articles at this page

Optimal Piecewise-based Mechanism for Collecting Bounded Numerical Data under Local Differential Privacy Revision Code Slides

Ye Zheng, Sumita Mishra, Yidan Hu
[PETS'25]: Privacy Enhancing Technologies Symposium ★ Artifact Award Runner-up

Locally Differentially Private Frequency Estimation via Joint Randomized Response Update Code Slides

Ye Zheng, Shafizur Rahman Seeam, Yidan Hu, Rui Zhang, Yanchao Zhang
[PETS'25]: Privacy Enhancing Technologies Symposium

MpBP: Verifying Robustness of Neural Networks with Multi-path Bound Propagation Code Slides Slides-2

Ye Zheng, Jiaxiang Liu, Xiaomu Shi
[FSE'22 Demonstrations]: European Software Engineering Conference and Symposium on the Foundations of Software Engineering

基于多路径回溯的神经网络验证方法 and the English journal version Multi-path Back-propagation Method for Neural Network Verification Code Slides

郑烨，施晓牧，刘嘉祥
[JOS'22] and [IJSI'22]: 软件学报 and International Journal of Software and Informatics

Biography

Rochester Institute of Technology (2023 – Present)

Ph.D. candidate in Computer Science
Research topics: AI Privacy and Differential Privacy (Formal Privacy), advised by Dr. Yidan Hu

Shenzhen University (2020 – 2023)

M.S. in Software Engineering
Research topics: Neural Network Verification (Formal Verification), advised by Dr. Jiaxiang Liu

Henan University (2016 – 2020)

B.S. in Mathematics
Majored in Pure Mathematics, advised by Dr. Zhonghua Wang

硕士学位论文《多路径方法在神经网络验证中的研究与应用》 Slides

本文关注神经网络验证方法中界限传播方法的精度问题。关于此问题，本文提出界限传播路径的概念，将各种界限传播方法扩展到其对应的多路径界限传播方法；此外，本文将多路径界限传播在 PyTorch 框架上并行化，开发了高效而易用的鲁棒性验证工具。