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

Bangzhou Xin; Wei Yang; Yangyang Geng; Sheng Chen; Shaowei Wang; Liusheng Huang

ICASSP 2020accepted0 citations

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

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

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.

BibTeX

@inproceedings{icassp2020_privateflgandiff,
  title = {Private FL-GAN: Differential Privacy Synthetic Data Generation Based on Federated Learning},
  author = {Bangzhou Xin and Wei Yang and Yangyang Geng and Sheng Chen and Shaowei Wang and Liusheng Huang},
  booktitle = {ICASSP 2020},
  year = {2020}
}