Using Adversarial Noises to Protect Privacy in Deep Learning Era

Liu, B; Ding, M; Zhu, T; Xiang, Y; Zhou, W

Using Adversarial Noises to Protect Privacy in Deep Learning Era

Liu, B

Ding, M Zhu, T

Xiang, Y Zhou, W

Permalink

Publication Type:: Conference Proceeding
Citation:: 2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings, 2018
Issue Date:: 2018-01-01

Closed Access

	Filename	Description	Size
	Using Adversarial Noises to Protect Privacy in Deep Learning Era.pdf	Published version	1.65 MB	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	Liu, B https://orcid.org/0000-0002-3603-6617	en_US
dc.contributor.author	Ding, M	en_US
dc.contributor.author	Zhu, T https://orcid.org/0000-0003-3411-7947	en_US
dc.contributor.author	Xiang, Y	en_US
dc.contributor.author	Zhou, W https://orcid.org/0000-0002-1680-2521	en_US
dc.date.issued	2018-01-01	en_US
dc.identifier.citation	2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings, 2018	en_US
dc.identifier.isbn	9781538647271	en_US
dc.identifier.uri	http://hdl.handle.net/10453/134401
dc.description.abstract	© 2018 IEEE. The unprecedented accuracy of deep learning methods has earned themselves as the foundation of new AI-based services on the Internet. At the same time, it presents obvious privacy issues. The deep learning aided privacy attack can dig out sensitive personal information not only from the text but also from unstructured data such as images and videos. In this paper, we proposed a framework to protect image privacy against the deep learning tools. We also propose two new metrics to measure the image privacy. Moreover, we propose two different image privacy protection schemes based on the two metrics, utilizing the adversarial example idea. The performance of our schemes is validated by simulation on a large-scale dataset. Our study shows that we can protect the image privacy by adding a small amount of noise, while the added noise has a humanly imperceptible impact on the image quality.	en_US
dc.relation.ispartof	2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings	en_US
dc.relation.isbasedon	10.1109/GLOCOM.2018.8647189	en_US
dc.title	Using Adversarial Noises to Protect Privacy in Deep Learning Era	en_US
dc.type	Conference Proceeding
utslib.for	0805 Distributed Computing	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

Abstract:

© 2018 IEEE. The unprecedented accuracy of deep learning methods has earned themselves as the foundation of new AI-based services on the Internet. At the same time, it presents obvious privacy issues. The deep learning aided privacy attack can dig out sensitive personal information not only from the text but also from unstructured data such as images and videos. In this paper, we proposed a framework to protect image privacy against the deep learning tools. We also propose two new metrics to measure the image privacy. Moreover, we propose two different image privacy protection schemes based on the two metrics, utilizing the adversarial example idea. The performance of our schemes is validated by simulation on a large-scale dataset. Our study shows that we can protect the image privacy by adding a small amount of noise, while the added noise has a humanly imperceptible impact on the image quality.

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

http://hdl.handle.net/10453/134401