Private FL-GAN: Differential Privacy Synthetic Data Generation Based on Federated Learning
Lists
Only you see this
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{xin2020private,
author = {Bangzhou Xin and Wei Yang and Yangyang Geng and Sheng Chen and Shaowei Wang and Liusheng Huang},
title = {{Private FL-GAN: Differential Privacy Synthetic Data Generation Based on Federated Learning}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2020},
url = {https://openreview.net/forum?id=uhXGkMGGDoe},
}Loading related content...