Private FL-GAN: Differential Privacy Synthetic Data Generation Based on Federated Learning

By Bangzhou Xin, Wei Yang, Yangyang Geng, Sheng Chen, Shaowei Wang, Liusheng Huang. 2020

104 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Patrick J. Tinsley
2. Patrick J. Flynn
3. Adam Czajka

Citations in the corpus

• This Face Does Not Exist... But It Might Be Yours! Identity Leakage in Generative Models (2020, background): “Since sensitivity regarding personal data leakage into machine learning models has been so well documented, several solutions have been developed to prevent such information leakage [29, 3, 27].”