Disentangling different levels of GAN fingerprints for task-specific forensics

Liu, C; Zhu, T; Zhao, Y; Zhang, J; Zhou, W

Disentangling different levels of GAN fingerprints for task-specific forensics

Liu, C Zhu, T

Zhao, Y Zhang, J Zhou, W

Permalink

Publisher:: Elsevier
Publication Type:: Journal Article
Citation:: Computer Standards and Interfaces, 2024, 89, pp. 103825
Issue Date:: 2024-04-01

Closed Access

	Filename	Description	Size
	1-s2.0-S092054892300106X-main.pdf	Published version	977.43 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	Liu, C
dc.contributor.author	Zhu, T https://orcid.org/0000-0003-3411-7947
dc.contributor.author	Zhao, Y
dc.contributor.author	Zhang, J
dc.contributor.author	Zhou, W
dc.date.accessioned	2024-03-01T02:31:09Z
dc.date.available	2024-03-01T02:31:09Z
dc.date.issued	2024-04-01
dc.identifier.citation	Computer Standards and Interfaces, 2024, 89, pp. 103825
dc.identifier.issn	0920-5489
dc.identifier.uri	http://hdl.handle.net/10453/176008
dc.description.abstract	Image generation using generative adversarial networks (GANs) has raised new security challenges recently. One promising forensic solution is verifying whether or not a suspicious image contains a GAN fingerprint, a unique trace left behind by the source GAN. Previous methods mainly focused on GAN fingerprint extraction while underestimating the downstream forensic applications, and the fingerprints are often single-level which only supports one specific forensic task. In this study, we investigate the problem of disentangling different levels of GAN fingerprints to satisfy the need for varying forensics tasks. Based on an analysis of fingerprint dependency revealing the existence of two levels of fingerprints in different signal domains, we proposed a decoupling representation framework to separate and extract two types of GAN fingerprints from different domains. An adversarial data augmentation strategy plus a transformation-invariant loss is added to the framework to enhance the robustness of fingerprints to image perturbations. Then we elaborated on three typical forensics tasks and the task-specific fingerprinting using different GAN fingerprints. Extensive experiments have verified our dependency analysis, the effectiveness and robustness of the proposed fingerprint extraction framework, and the applicability of task-specific fingerprinting in real-world and simulated scenarios.
dc.language	en
dc.publisher	Elsevier
dc.relation	http://purl.org/au-research/grants/arc/DP230100246
dc.relation.ispartof	Computer Standards and Interfaces
dc.relation.isbasedon	10.1016/j.csi.2023.103825
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0803 Computer Software, 0804 Data Format, 0805 Distributed Computing
dc.subject.classification	Information Systems
dc.subject.classification	40 Engineering
dc.subject.classification	46 Information and computing sciences
dc.title	Disentangling different levels of GAN fingerprints for task-specific forensics
dc.type	Journal Article
utslib.citation.volume	89
utslib.for	0803 Computer Software
utslib.for	0804 Data Format
utslib.for	0805 Distributed Computing
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	closed_access	*
dc.date.updated	2024-03-01T02:31:05Z
pubs.publication-status	Accepted
pubs.volume	89

Abstract:

Image generation using generative adversarial networks (GANs) has raised new security challenges recently. One promising forensic solution is verifying whether or not a suspicious image contains a GAN fingerprint, a unique trace left behind by the source GAN. Previous methods mainly focused on GAN fingerprint extraction while underestimating the downstream forensic applications, and the fingerprints are often single-level which only supports one specific forensic task. In this study, we investigate the problem of disentangling different levels of GAN fingerprints to satisfy the need for varying forensics tasks. Based on an analysis of fingerprint dependency revealing the existence of two levels of fingerprints in different signal domains, we proposed a decoupling representation framework to separate and extract two types of GAN fingerprints from different domains. An adversarial data augmentation strategy plus a transformation-invariant loss is added to the framework to enhance the robustness of fingerprints to image perturbations. Then we elaborated on three typical forensics tasks and the task-specific fingerprinting using different GAN fingerprints. Extensive experiments have verified our dependency analysis, the effectiveness and robustness of the proposed fingerprint extraction framework, and the applicability of task-specific fingerprinting in real-world and simulated scenarios.

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

http://hdl.handle.net/10453/176008