Article (Scientific journals)
UNTAG: Learning Generic Features for Unsupervised Type-Agnostic Deepfake Detection
Mejri, Nesryne; Ghorbel, Enjie; Aouada, Djamila
2023In IEEE International Conference on Acoustics, Speech and Signal Processing. Proceedings
Peer reviewed
 

Files


Full Text
2023044110.pdf
Author preprint (2.02 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Type-agnostic Deepfake Detection; Unsupervised classification
Abstract :
[en] This paper introduces a novel framework for unsupervised type-agnostic deepfake detection called UNTAG. Existing methods are generally trained in a supervised manner at the classification level, focusing on detecting at most two types of forgeries; thus, limiting their generalization capability across different deepfake types. To handle that, we reformulate the deepfake detection problem as a one-class classification supported by a self-supervision mechanism. Our intuition is that by estimating the distribution of real data in a discriminative feature space, deepfakes can be detected as outliers regardless of their type. UNTAG involves two sequential steps. First, deep representations are learned based on a self-supervised pretext task focusing on manipulated regions. Second, a one-class classifier fitted on authentic image embeddings is used to detect deepfakes. The results reported on several datasets show the effectiveness of UNTAG and the relevance of the proposed new paradigm. The code is publicly available.
Research center :
- Interdisciplinary Centre for Security, Reliability and Trust (SnT) > CVI² - Computer Vision Imaging & Machine Intelligence
Disciplines :
Computer science
DOI :
10.1109/ICASSP49357.2023.10095983
Author, co-author :
Mejri, Nesryne  ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > CVI2
Ghorbel, Enjie  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
Aouada, Djamila  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
External co-authors :
no
Language :
English
Title :
UNTAG: Learning Generic Features for Unsupervised Type-Agnostic Deepfake Detection
Publication date :
08 June 2023
Journal title :
IEEE International Conference on Acoustics, Speech and Signal Processing. Proceedings
ISSN :
1520-6149
Publisher :
IEEE. Institute of Electrical and Electronics Engineers, Greece
Peer reviewed :
Peer reviewed
Focus Area :
Computational Sciences
FnR Project :
FNR16763798 - Unsupervised Multi-type Explainable Deepfake Detection, 2021 (01/10/2021-31/08/2025) - Nesryne Mejri
Name of the research project :
UNsupervised multi-type explainable deepFAKE detection (UNFAKE)
Funders :
FNR - Fonds National de la Recherche [LU]
Available on ORBilu :
since 06 March 2023

Statistics


Number of views
146 (33 by Unilu)
Number of downloads
20 (7 by Unilu)

Scopus citations®
 
2
Scopus citations®
without self-citations
1

Bibliography


Similar publications



Contact ORBilu