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

Qu, Y; Yu, S; Zhang, J; Binh, HTT; Gao, L; Zhou, W

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

Qu, Y Yu, S

Zhang, J Binh, HTT Gao, L Zhou, W

Permalink

Publication Type:: Conference Proceeding
Citation:: IEEE International Conference on Communications, 2019, 2019-May
Issue Date:: 2019-05-01

Closed Access

	Filename	Description	Size
	GAN_DP Generative Adversarial Net Driven.pdf	Published version	563.07 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Qu, Y	en_US
dc.contributor.author	Yu, S https://orcid.org/0000-0003-4485-6743	en_US
dc.contributor.author	Zhang, J	en_US
dc.contributor.author	Binh, HTT	en_US
dc.contributor.author	Gao, L	en_US
dc.contributor.author	Zhou, W https://orcid.org/0000-0002-1680-2521	en_US
dc.date.issued	2019-05-01	en_US
dc.identifier.citation	IEEE International Conference on Communications, 2019, 2019-May	en_US
dc.identifier.isbn	9781538680889	en_US
dc.identifier.issn	1550-3607	en_US
dc.identifier.uri	http://hdl.handle.net/10453/136897
dc.description.abstract	© 2019 IEEE. 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.	en_US
dc.relation.ispartof	IEEE International Conference on Communications	en_US
dc.relation.isbasedon	10.1109/ICC.2019.8761070	en_US
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	GAN-DP: Generative Adversarial Net Driven Differentially Privacy-Preserving Big Data Publishing	en_US
dc.type	Conference Proceeding
utslib.citation.volume	2019-May	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
pubs.publication-status	Published	en_US
pubs.volume	2019-May	en_US

Abstract:

© 2019 IEEE. 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.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/136897