Ppgan: Privacy-preserving generative adversarial network

Liu，Yi1; Peng，Jialiang1; Yu，James J.Q.2; Wu，Yi1

10.1109/ICPADS47876.2019.00150

2019-12-01

1521-9097

978-1-7281-2584-8

Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS

2019-December

985-989

4-6 Dec. 2019

Tianjin, China

10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA

IEEE Computer Society

Generative Adversarial Network (GAN) and its variants serve as a perfect representation of the data generation model, providing researchers with a large amount of high-quality generated data. They illustrate a promising direction for research with limited data availability. When GAN learns the semantic-rich data distribution from a dataset, the density of the generated distribution tends to concentrate on the training data. Due to the gradient parameters of the deep neural network contain the data distribution of the training samples, they can easily remember the training samples. When GAN is applied to private or sensitive data, for instance, patient medical records, as private information may be leakage. To address this issue, we propose a Privacy-preserving Generative Adversarial Network (PPGAN) model, in which we achieve differential privacy in GANs by adding well-designed noise to the gradient during the model learning procedure. Besides, we introduced the Moments Accountant strategy in the PPGAN training process to improve the stability and compatibility of the model by controlling privacy loss. We also give a mathematical proof of the differential privacy discriminator. Through extensive case studies of the benchmark datasets, we demonstrate that PPGAN can generate high-quality synthetic data while retaining the required data available under a reasonable privacy budget.

Deep learning Differential privacy GAN Moments accountant Privacy leakage

其他

英语

EI ; CPCI-S

Ministry of Education of China[201910212133]

Computer Science

Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods

WOS:000530854900141

20200608137083

Benchmarking ; Budget control ; Deep learning ; Sampling ; Semantics

Ergonomics and Human Factors Engineering:461.4 ; Telecommunication; Radar, Radio and Television:716 ; Telephone Systems and Related Technologies; Line Communications:718 ; Data Processing and Image Processing:723.2 ; Artificial Intelligence:723.4

2-s2.0-85078950786

Scopus

1.School of Data Science and Technology,Heilongjiang University,China
2.Department of Computer Science and Engineering,Southern University of Science and Technology,China

Liu，Yi,Peng，Jialiang,Yu，James J.Q.,et al. Ppgan: Privacy-preserving generative adversarial network[C]. 10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA:IEEE Computer Society,2019:985-989.