LabelDP-Pro: Learning with Label Differential Privacy via Projections

Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Chiyuan Zhang

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Differential Privacy, Label Differential Privacy, Projections

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We propose a family of label DP training algorithms that use projections to denoise the private gradients and achieve better utility in the high-privacy regime.

Abstract: Label differentially private (label DP) algorithms seek to preserve the privacy of the labels in a training dataset in settings where the features are known to the adversary. In this work, we study a new family of label DP training algorithms. Unlike most prior label DP algorithms that have been based on label randomization, our algorithm naturally leverages the power of the central model of DP. It interleaves gradient projection operations with private stochastic gradient descent steps in order to improve the utility of the trained model while guaranteeing the privacy of the labels. We show that such projection-based algorithms can be made practical and that they improve on the state-of-the art for label DP training in the high-privacy regime. We complement our empirical evaluation with theoretical results shedding light on the efficacy of our method through the lens of bias-variance trade-offs.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: societal considerations including fairness, safety, privacy

Submission Number: 4094