SecureGAN: Secure Three-Party GAN Training

Generating Adversarial Network (GAN) is a prominent unsupervised learning method that utilizes two competing neural networks to generate realistic data, which has been widely employed in image synthesis and data augmentation. Outsourcing GAN training to cloud servers can significantly reduce the computation load on local devices. Furthermore, in outsourcing settings, training data can be gathered from multiple users, leading to larger amounts of data and, as a result, improved training accuracy. However, outsourcing is associated with privacy risks, as training data often contains sensitive information. To address this problem, we propose SecureGAN, a privacy-preserving framework for GAN that aims to protect the privacy of the training input and output. We implement secure protocols based on replicated secret sharing technology to protect the privacy of the linear and nonlinear layers. We conduct experiments using the MP-SPDZ framework, and the results demonstrate the effectiveness of the proposed protocols.

I. Introduction

Generative Adversarial Network (GAN) [1] is a deep learning model proficient in generating images. Unlike traditional generative models, GAN employs a way of mutual game between the generator and the discriminator, constantly improving the performance of the generator and producing high-quality synthetic images. This technology has been widely applied in computer vision, image processing, and numerous other fields.