Protecting Multimedia Privacy from Both Humans and AI

Liu, B; Xiong, J; Wu, Y; Ding, M; Wu, CM

Protecting Multimedia Privacy from Both Humans and AI

Liu, B

Xiong, J Wu, Y Ding, M Wu, CM

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB, 2019, 2019-June
Issue Date:: 2019-06-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

The embargo period expires on 1 Jun 2022

Adobe PDF

Download Accepted versionAdobe PDF (2.47 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Liu, B https://orcid.org/0000-0002-3603-6617
dc.contributor.author	Xiong, J
dc.contributor.author	Wu, Y
dc.contributor.author	Ding, M
dc.contributor.author	Wu, CM
dc.date	2019-06-05
dc.date.accessioned	2020-05-14T06:39:16Z
dc.date.available	2020-05-14T06:39:16Z
dc.date.issued	2019-06-01
dc.identifier.citation	IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB, 2019, 2019-June
dc.identifier.isbn	9781728121505
dc.identifier.issn	2155-5044
dc.identifier.issn	2155-5052
dc.identifier.uri	http://hdl.handle.net/10453/140721
dc.description.abstract	© 2019 IEEE. With the development of artificial intelligence (AI), multimedia privacy issues have become more challenging than ever. AI-assisted malicious entities can steal private information from multimedia data more easily than humans. Traditional multimedia privacy protection only considers the situation when humans are the adversaries, therefore they are ineffective against AI-assisted attackers. In this paper, we develop a new framework and new algorithms that can protect image privacy from both humans and AI. We combine the idea of adversarial image perturbation which is effective against AI and the obfuscation technique for human adversaries. Experiments show that our proposed methods work well for all types of attackers.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB
dc.relation.ispartof	2019 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)
dc.relation.isbasedon	10.1109/BMSB47279.2019.8971914
dc.rights	© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.	en_US
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.title	Protecting Multimedia Privacy from Both Humans and AI
dc.type	Conference Proceeding
utslib.citation.volume	2019-June
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
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	open_access	*
utslib.copyright.embargo	2022-06-01T00:00:00+1000Z
dc.date.updated	2020-05-14T06:39:05Z
pubs.finish-date	2019-06-07
pubs.publication-status	Published
pubs.start-date	2019-06-05
pubs.volume	2019-June

Abstract:

© 2019 IEEE. With the development of artificial intelligence (AI), multimedia privacy issues have become more challenging than ever. AI-assisted malicious entities can steal private information from multimedia data more easily than humans. Traditional multimedia privacy protection only considers the situation when humans are the adversaries, therefore they are ineffective against AI-assisted attackers. In this paper, we develop a new framework and new algorithms that can protect image privacy from both humans and AI. We combine the idea of adversarial image perturbation which is effective against AI and the obfuscation technique for human adversaries. Experiments show that our proposed methods work well for all types of attackers.

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

http://hdl.handle.net/10453/140721