GAN-DP: Generative Adversarial Net Driven Differentially Privacy-Preserving Big Data Publishing

Increasing massive volume of data are generated every single second in this big data era. With big data from multiple sources, adversaries continuously mine private information for potential benefits. Motivated by this, we propose a generative adversarial net (GAN) driven noise generation method und...

Full description

Saved in:
Bibliographic Details
Main Authors: Qu, Youyang, Yu, Shui, Zhang, Jingwen, Binh, Huynh Thi Thanh, Gao, Longxiang, Zhou, Wanlei
Format: Conference Proceeding
Language:English
Subjects:
Big Data
Differential privacy
Gallium nitride
Games
Generators
Privacy
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Increasing massive volume of data are generated every single second in this big data era. With big data from multiple sources, adversaries continuously mine private information for potential benefits. Motivated by this, we propose a generative adversarial net (GAN) driven noise generation method under the framework of differential privacy. We add one more perceptron, which is a specifically devised differential privacy identifier. After the generator produces the noise, the discriminator and the proposed identifier game with each other to derive the Nash Equilibrium. Extensive experimental results demonstrate the proposed model meets differential privacy constraints and upgrade data utility simultaneously.
ISSN:1938-1883
DOI:10.1109/ICC.2019.8761070