Large-Scale Public Data Improves Differentially Private Image Generation Quality

TL;DR

This paper demonstrates that large-scale public data can significantly enhance the quality of differentially private image generation using GANs, achieving state-of-the-art results in FID scores and image realism.

Contribution

The authors propose a novel method that effectively leverages public data to improve differentially private GANs, assuming the public data supports the private data distribution.

Findings

Achieves state-of-the-art FID scores in private image generation

Generates high-quality, photo-realistic images with differential privacy

Outperforms existing methods using public data in privacy-preserving image synthesis

Abstract

Public data has been frequently used to improve the privacy-accuracy trade-off of differentially private machine learning, but prior work largely assumes that this data come from the same distribution as the private. In this work, we look at how to use generic large-scale public data to improve the quality of differentially private image generation in Generative Adversarial Networks (GANs), and provide an improved method that uses public data effectively. Our method works under the assumption that the support of the public data distribution contains the support of the private; an example of this is when the public data come from a general-purpose internet-scale image source, while the private data consist of images of a specific type. Detailed evaluations show that our method achieves SOTA in terms of FID score and other metrics compared with existing methods that use public data, and can generate high-quality, photo-realistic images in a differentially private manner.