Training generative models from privatized data. (arXiv:2306.09547v1 [cs.LG])

Local differential privacy (LDP) is a powerful method for privacy-preserving
data collection. In this paper, we develop a framework for training Generative
Adversarial Networks (GAN) on differentially privatized data. We show that
entropic regularization of the Wasserstein distance -- a popular regularization
method in the literature that has been often leveraged for its computational
benefits -- can be used to denoise the data distribution when data is
privatized by common additive noise mechanisms, such as Laplace and Gaussian.
This combination …

adversarial collection data data collection differential privacy framework gan generative generative adversarial networks literature local networks popular privacy training