Private FL-GAN: Differential Privacy Synthetic Data Generation Based on Federated Learning
Authors:
- 1 May 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2927-2931
Abstract
Generative Adversarial Network (GAN) has already made a big splash in the field of generating realistic "fake" data. However, when data is distributed and data-holders are reluctant to share data for privacy reasons, GAN’s training is difficult. To address this issue, we propose private FL-GAN, a differential privacy generative adversarial network model based on federated learning. By strategically combining the Lipschitz limit with the differential privacy sensitivity, the model can generate high-quality synthetic data without sacrificing the privacy of the training data. We theoretically prove that private FL-GAN can provide strict privacy guarantee with differential privacy, and experimentally demonstrate our model can generate satisfactory data.Keywords
This publication has 7 references indexed in Scilit:
- MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets2019
- GANobfuscator: Mitigating Information Leakage Under GAN via Differential PrivacyIEEE Transactions on Information Forensics and Security, 2019
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network2017
- Deep Learning with Differential Privacy2016
- Deep learningNature, 2015
- The Algorithmic Foundations of Differential PrivacyFoundations and Trends® in Theoretical Computer Science, 2014
- Calibrating Noise to Sensitivity in Private Data Analysis2006