Liyang Xie, Kaixiang Lin, Shu Wang, Fei Wang, Jiayu Zhou
TL;DR本文通过在学习过程中添加特别设计的梯度噪声来实现差分隐私的生成对抗网络(DPGAN),以解决 GAN 在应用于私人或敏感数据时可能泄露关键信息的问题,并提供隐私保障的严格证明和全面的实证证据。
Abstract
generative adversarial network (gan) and its variants have recently attracted
intensive research interests due to their elegant theoretical foundation and
excellent empirical performance as generative models. The