| Title | Private FL-GAN: Differential Privacy Synthetic Data Generation Based on Federated Learning |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Xin, B., Yang, W., Geng, Y., Chen, S., Wang, S., Huang, L. |
| Conference Name | ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
| Keywords | composability, data generation, data handling, data privacy, data sharing, data-holders, Differential privacy, differential privacy generative adversarial network model, differential privacy sensitivity, differential privacy synthetic data generation, federated learning, GAN training, high-quality synthetic data generation, Human Behavior, Information security, learning (artificial intelligence), Lipschitz limit, neural nets, private FL-GAN, pubcrawl, realistic fake data generation, Resiliency, Scalability, security of data, strict privacy guarantee |
| 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. |
| DOI | 10.1109/ICASSP40776.2020.9054559 |
| Citation Key | xin_private_2020 |
Private FL-GAN: Differential Privacy Synthetic Data Generation Based on Federated Learning