About Me

I'm Da Yu, a PhD student at Sun Yat-sen University since 2019, advised by Prof. Jian Yin and Prof. Tie-Yan Liu. Before that, I received my B.S. degree of Computer Science from Sun Yat-sen University in 2019.

Currently, I am a research intern at Microsoft Research Asia, advised by Dr. Huishuai Zhang. I'm broadly interested in the aspects of trustworthy deep learning, e.g., privacy and security issues of deep learning. My research is supported by MSRA Fellowship.

Email: yuda3@?.sysu.edu.cn, but replace ? with mail2.

Publications

Per-Instance Privacy Accounting for Differentially Private Stochastic Gradient Descent

Da Yu, Gautam Kamath*, Janardhan Kulkarni*, Tie-Yan Liu*, Jian Yin*, Huishuai Zhang* (* denotes alphabetical order).

Preprint, 2022.

Availability Attacks Create Shortcuts

Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu.

SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Research Track, 2022.

Differentially Private Fine-tuning of Language Models

Da Yu, Saurabh Naik, Arturs Backurs*, Sivakanth Gopi*, Huseyin A. Inan*, Gautam Kamath*, Janardhan Kulkarni*, Yin Tat Lee*, Andre Manoel*, Lukas Wutschitz*, Sergey Yekhanin*, Huishuai Zhang* (* denotes alphabetical order).

International Conference on Learning Representations (ICLR), 2022.

Large Scale Private Learning via Low-rank Reparametrization

Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu.

International Conference on Machine Learning (ICML), 2021.

Do not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning

Da Yu*, Huishuai Zhang*, Wei Chen, Tie-Yan Liu.

International Conference on Learning Representations (ICLR), 2021.

How Does Data Augmentation Affect Privacy in Machine Learning?

Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu.

AAAI Conference on Artificial Intelligence (AAAI), 2021.

Gradient Perturbation is Underrated for Differentially Private Convex Optimization

Da Yu*, Huishuai Zhang*, Wei Chen, Jian Yin, Tie-Yan Liu.

International Joint Conference on Artificial Intelligence (IJCAI), 2020.

Convergence Theory of Learning Over-parameterized ResNet: A Full Characterization

Huishuai Zhang, Da Yu, Mingyang Yi, Wei Chen, Tie-Yan Liu

Preprint, 2019.

Improve the Gradient Perturbation Approach for Differentially Private Optimization

Da Yu, Huishuai Zhang, Wei Chen.

Privacy Preserving Machine Learning, NeurIPS Workshop, 2018.