DPAF: Image Synthesis via Differentially Private Aggregation in Forward Phase

Chih-Hsun Lin, Chia-Yi Hsu, Chia-Mu Yu, YANG CAO, Chun-Ying Huang

Keywords: Differential Privacy, Synthetic Data, DPSGD, Generative Adversarial Network

TL;DR: We propose DPAF, an DP generative model for high-dimensional image synthesis. DPAF adds DP feature aggregation in the forward phase, which brings advantages such as reducing information loss in gradient clipping and low sensitivity to aggregation.

Abstract: Differentially private synthetic data is a promising alternative for sensitive data release. Many differentially private generative models have been proposed in the literature. Unfortunately, they all suffer from the low utility of the synthetic data, especially for high resolution images. Here, we propose DPAF, an effective differentially private generative model for high-dimensional image synthesis. Unlike previous methods, which add Gaussian noise in the \textit{backward} phase during model training, DPAF adds differentially private feature aggregation in the \textit{forward} phase, which brings advantages such as reducing information loss in gradient clipping and low sensitivity to aggregation. Since an inappropriate batch size has a negative impact on the utility of synthetic data, DPAF also addresses the problem of setting an appropriate batch size by proposing a novel training strategy that asymmetrically trains different parts of the discriminator. We extensively evaluate different methods on multiple image datasets (up to images of $128\times 128$ resolution) to demonstrate the performance of DPAF.

Primary Area: societal considerations including fairness, safety, privacy

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.

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

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.

Submission Number: 6113