DPGOMI: Differentially Private Data Publishing with Gaussian Optimized Model Inversion
This addresses privacy concerns for data publishers in deep learning applications, but it is incremental as it builds on existing DP-GAN methods.
The paper tackled the problem of releasing high-dimensional sensitive data with privacy protection by proposing DPGOMI, a differentially private method that maps data to a latent space and uses a lower-dimensional DP-GAN. Results showed DPGOMI outperformed standard DP-GAN on CIFAR10 and SVHN datasets in Inception Score, Fréchet Inception Distance, and classification performance while maintaining the same privacy level.
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, Fréchet 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.