Differentially Private Generative Adversarial Networks with Model Inversion.
Differentially Private Generative Adversarial Networks with Model Inversion.
复制标题
DOI：
10.1109/wifs53200.2021.9648378
复制
发表时间：
2021-12
期刊：
影响因子：
--
通讯作者：
Ozonoff, Sally
中科院分区：
文献类型：
--
作者：
Chen, Dongjie;Cheung, Sen-ching Samson;Chuah, Chen-Nee;Ozonoff, Sally
To protect sensitive data in training a Generative Adversarial Network (GAN), the standard approach is to use differentially private (DP) stochastic gradient descent method in which controlled noise is added to the gradients. The quality of the output synthetic samples can be adversely affected and the training of the network may not even converge in the presence of these noises. We propose Differentially Private Model Inversion (DPMI) method where the private data is first mapped to the latent space via a public generator, followed by a lower-dimensional DP-GAN with better convergent properties. Experimental results on standard datasets CIFAR10 and SVHN as well as on a facial landmark dataset for Autism screening show that our approach outperforms the standard DP-GAN method based on Inception Score, Frechet Inception Distance, and classification accuracy under the same privacy guarantee.
登录
查看更多内容
DOI：
10.1109/tifs.2019.2897874
发表时间：
2019-09-01
影响因子：
6.8
作者：
Xu, Chugui;Ren, Ju;Ren, Kui
通讯作者：
Ren, Kui
DOI：
10.1161/circoutcomes.118.005122
发表时间：
2019-07-01
影响因子：
6.9
作者：
Beaulieu-Jones, Brett K.;Wu, Zhiwei Steven;Greene, Casey S.
通讯作者：
Greene, Casey S.
影响因子：
22.7
作者：
Goodfellow, Ian;Pouget-Abadie, Jean;Bengio, Yoshua
通讯作者：
Bengio, Yoshua
DOI：
10.1016/j.jaac.2009.11.009
发表时间：
2010-03-01
影响因子：
13.3
作者：
Ozonoff, Sally;Iosif, Ana-Maria;Young, Gregory S.
通讯作者：
Young, Gregory S.
影响因子：
--
作者：
Dwork, Cynthia;Roth, Aaron
通讯作者：
Roth, Aaron