DPGOMI: Differentially Private Data Publishing with Gaussian Optimized Model Inversion

TL;DR

This paper introduces DPGOMI, a novel differentially private data publishing method that uses Gaussian optimized model inversion to protect sensitive data while maintaining high data utility in deep learning applications.

Contribution

The paper proposes a new approach combining latent space mapping and a specialized DP-GAN to improve privacy and data quality in differentially private data publishing.

Findings

DPGOMI outperforms standard DP-GAN in quality metrics

Maintains privacy while improving classification performance

Effective on datasets CIFAR10 and SVHN

Abstract

High-dimensional data are widely used in the era of deep learning with numerous applications. However, certain data which has sensitive information are not allowed to be shared without privacy protection. In this paper, we propose a novel differentially private data releasing method called Differentially Private Data Publishing with Gaussian Optimized Model Inversion (DPGOMI) to address this issue. Our approach involves mapping private data to the latent space using a public generator, followed by a lower-dimensional DP-GAN with better convergence properties. We evaluate the performance of DPGOMI on standard datasets CIFAR10 and SVHN. Our results show that DPGOMI outperforms the standard DP-GAN method in terms of Inception Score, Fr\'echet Inception Distance, and classification performance, while providing the same level of privacy. Our proposed approach offers a promising solution for protecting sensitive data in GAN training while maintaining high-quality results.