差别隐私
计算机科学
生成对抗网络
信息隐私
极限(数学)
数据建模
对抗制
李普希茨连续性
生成模型
计算机安全
生成语法
数据挖掘
深度学习
人工智能
数学
数据库
数学分析
作者
Bangzhou Xin,Wei Yang,Yangyang Geng,Sheng Chen,Shaowei Wang,Liusheng Huang
标识
DOI:10.1109/icassp40776.2020.9054559
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI