Identity-Consistent Video De-identification via Diffusion Autoencoders

Zhu, Y; Cao, J; Liu, B; Chen, T; Xie, R; Song, L

Identity-Consistent Video De-identification via Diffusion Autoencoders

Zhu, Y Cao, J Liu, B

Chen, T Xie, R Song, L

Permalink

Publisher:: Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:: Conference Proceeding
Citation:: IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB, 2024, 00, pp. 1-6
Issue Date:: 2024-01-01

Recently Added

	Filename	Description	Size
	BMSB_2024_Paper80.pdf	Accepted version	1.51 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is new to OPUS and is not currently available.

Full metadata record

Field	Value	Language
dc.contributor.author	Zhu, Y
dc.contributor.author	Cao, J
dc.contributor.author	Liu, B https://orcid.org/0000-0002-3603-6617
dc.contributor.author	Chen, T
dc.contributor.author	Xie, R
dc.contributor.author	Song, L
dc.date	2024-06-19
dc.date.accessioned	2024-09-05T23:11:01Z
dc.date.available	2024-09-05T23:11:01Z
dc.date.issued	2024-01-01
dc.identifier.citation	IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB, 2024, 00, pp. 1-6
dc.identifier.issn	2155-5044
dc.identifier.issn	2155-5052
dc.identifier.uri	http://hdl.handle.net/10453/180726
dc.description.abstract	With the rise of deep learning and the widespread use of face recognition, face image privacy has become a critical research issue. Face de-identification is acknowledged as effective for protecting identity privacy. As media formats diversify, it is imperative to extend privacy protection to videos. Addressing the core problem of identity consistency between frames, we propose a video de-identification approach based on the diffusion model. We disentangle video features with a diffusion autoencoder, where the identity and motion features are encoded into high-level semantic spaces while background and other facial identity-independent features into low-dimensional random subcodes. The unified time-independent identity representation is used to achieve coherent video de-identification results. Compared to existing methods, our proposed approach demonstrates superior performance in terms of privacy protection effectiveness, identity consistency between frames, and utility.
dc.language	en
dc.publisher	Institute of Electrical and Electronics Engineers (IEEE)
dc.relation.ispartof	IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB
dc.relation.ispartof	2024 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)
dc.relation.isbasedon	10.1109/BMSB62888.2024.10608204
dc.rights	info:eu-repo/semantics/restrictedAccess
dc.title	Identity-Consistent Video De-identification via Diffusion Autoencoders
dc.type	Conference Proceeding
utslib.citation.volume	00
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/Strength - AAII - Australian Artificial Intelligence Institute
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	University of Technology Sydney/Strength - CCSP - Centre for Cyber Security and Privacy
utslib.copyright.status	recently_added	*
dc.date.updated	2024-09-05T23:10:56Z
pubs.finish-date	2024-06-21
pubs.publication-status	Published
pubs.start-date	2024-06-19
pubs.volume	00

Abstract:

With the rise of deep learning and the widespread use of face recognition, face image privacy has become a critical research issue. Face de-identification is acknowledged as effective for protecting identity privacy. As media formats diversify, it is imperative to extend privacy protection to videos. Addressing the core problem of identity consistency between frames, we propose a video de-identification approach based on the diffusion model. We disentangle video features with a diffusion autoencoder, where the identity and motion features are encoded into high-level semantic spaces while background and other facial identity-independent features into low-dimensional random subcodes. The unified time-independent identity representation is used to achieve coherent video de-identification results. Compared to existing methods, our proposed approach demonstrates superior performance in terms of privacy protection effectiveness, identity consistency between frames, and utility.

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

http://hdl.handle.net/10453/180726