PPGAN: Privacy-preserving Generative Adversarial Network

Abstract

Generative Adversarial Network (GAN) and its variants serve as a perfect representation of the data generation model, providing researchers with a large amount of high-quality generated data. They illustrate a promising direction for research with limited data availability. When GAN learns the semantic-rich data distribution from a dataset, the density of the generated distribution tends to concentrate on the training data. Due to the gradient parameters of the deep neural network contain the data distribution of the training samples, they can easily remember the training samples. When GAN is applied to private or sensitive data, for instance, patient medical records, as private information may be leakage. To address this issue, we propose a Privacy-preserving Generative Adversarial Network (PPGAN) model, in which we achieve differential privacy in GANs by adding well-designed noise to the gradient during the model learning procedure. Besides, we introduced the Moments Accountant strategy in the PPGAN training process to improve the stability and compatibility of the model by controlling privacy loss. We also give a mathematical proof of the differential privacy discriminator. Through extensive case studies of the benchmark datasets, we demonstrate that PPGAN can generate high-quality synthetic data while retaining the required data available under a reasonable privacy budget.

arXiv commentThis paper was accepted by IEEE ICPADS 2019 Workshop. This paper contains 10 pages, 3 figures

References in corpus (7)

• Deep Learning with Differential Privacy
• Wasserstein GAN
• Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
• Differentially Private Generative Adversarial Network
• Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
• Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning
• Gaussian Differential Privacy

Cited by in corpus (11)

• Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art
• FedDPGAN: Federated Differentially Private Generative Adversarial Networks Framework for the Detection of COVID-19 Pneumonia
• Copyright in Generative Deep Learning
• Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey
• Towards Communication-efficient and Attack-Resistant Federated Edge Learning for Industrial Internet of Things
• Generative Adversarial Networks: A Survey Towards Private and Secure Applications
• Generating Synthetic Health Sensor Data for Privacy-Preserving Wearable Stress Detection
• A GAN-based Approach for Mitigating Inference Attacks in Smart Home Environment
• Integrating Homomorphic Encryption and Synthetic Data in FL for Privacy and Learning Quality
• HydraGAN A Multi-head, Multi-objective Approach to Synthetic Data Generation
• Causally Constrained Data Synthesis for Private Data Release