Da Yu
Cited by
Cited by
Differentially private fine-tuning of language models
D Yu, S Naik, A Backurs, S Gopi, HA Inan, G Kamath, J Kulkarni, YT Lee, ...
arXiv preprint arXiv:2110.06500, 2021
Do not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning
D Yu, H Zhang, W Chen, TY Liu
International Conference on Learning Representations (ICLR-21), 2021
Large Scale Private Learning via Low-rank Reparametrization
D Yu, H Zhang, W Chen, J Yin, TY Liu
International Conference on Machine Learning (ICML-21), 2021
How Does Data Augmentation Affect Privacy in Machine Learning?
D Yu, H Zhang, W Chen, J Yin, TY Liu
AAAI Conference on Artificial Intelligence (AAAI-21), 2020
Availability attacks create shortcuts
D Yu, H Zhang, W Chen, J Yin, TY Liu
Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and …, 2022
Gradient perturbation is underrated for differentially private convex optimization
D Yu, H Zhang, W Chen, TY Liu, J Yin
International Joint Conference on Artificial Intelligence (IJCAI-20), 2019
Stabilize deep ResNet with a sharp scaling factor
H Zhang, D Yu, M Yi, W Chen, TY Liu
Machine Learning 111 (9), 3359-3392, 2022
Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping
J He, X Li, D Yu, H Zhang, J Kulkarni, YT Lee, A Backurs, N Yu, J Bian
arXiv preprint arXiv:2212.01539, 2022
Improve the Gradient Perturbation Approach for Differentially Private Optimization
D Yu, H Zhang, W Chen
Privacy Preserving Machine Learning (NeurIPS 2018 Workshop), 0
Per-instance privacy accounting for differentially private stochastic gradient descent
D Yu, G Kamath, J Kulkarni, J Yin, TY Liu, H Zhang
arXiv preprint arXiv:2206.02617, 2022
Challenges towards the Next Frontier in Privacy
R Cummings, D Desfontaines, D Evans, R Geambasu, M Jagielski, ...
arXiv preprint arXiv:2304.06929, 2023
Selective Pre-training for Private Fine-tuning
D Yu, S Gopi, J Kulkarni, Z Lin, S Naik, TL Religa, J Yin, H Zhang
arXiv preprint arXiv:2305.13865, 2023
Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks
H Zhang, D Yu, Y Lu, D He
International Conference on Artificial Intelligence and Statistics, 2792-2804, 2023
On the Stability of Multi-branch Network
H Zhang, D Yu, W Chen, TY Liu
The system can't perform the operation now. Try again later.
Articles 1–14