DeepFakes detection across generations: Analysis of facial regions, fusion, and performance evaluation

Media forensics has attracted a tremendous attention in the last years in part due to the increasing concerns around DeepFakes. Since the release of the initial DeepFakes databases of the 1st generation such as UADFV and FaceForensics++ up to the latest databases of the 2nd generation such as Celeb-...

Full description

Bibliographic Details
Authors: Tolosana Moranchel, Rubén, Romero Tapiador, Sergio, Gonzalez Sosa, Vera Rodríguez, Rubén, Fiérrez Aguilar, Julián
Format: article
Publication Date:2022
Country:España
Institution:Universidad Autónoma de Madrid
Repository:Biblos-e Archivo. Repositorio Institucional de la UAM
Language:English
OAI Identifier:oai:repositorio.uam.es:10486/702775
Online Access:http://hdl.handle.net/10486/702775
https://dx.doi.org/10.1016/j.engappai.2022.104673
Access Level:Open access
Keyword:Benchmark
Databases
DeepFakes
Face manipulation
Fake detection
Fake news
Media forensics
Telecomunicaciones
id ES_a1bb129a3e1e15b94a4cf45ba321cae7
oai_identifier_str oai:repositorio.uam.es:10486/702775
network_acronym_str ES
network_name_str España
repository_id_str
spelling DeepFakes detection across generations: Analysis of facial regions, fusion, and performance evaluationTolosana Moranchel, RubénRomero Tapiador, SergioGonzalez SosaVera Rodríguez, RubénFiérrez Aguilar, JuliánBenchmarkDatabasesDeepFakesFace manipulationFake detectionFake newsMedia forensicsTelecomunicacionesMedia forensics has attracted a tremendous attention in the last years in part due to the increasing concerns around DeepFakes. Since the release of the initial DeepFakes databases of the 1st generation such as UADFV and FaceForensics++ up to the latest databases of the 2nd generation such as Celeb-DF and DFDC, many visual improvements have been carried out, making fake videos almost indistinguishable to the human eye. This study provides an in-depth analysis of both 1st and 2nd DeepFakes generations in terms of fake detection performance. Two different methods are considered in our experimental framework: (i) the traditional one followed in the literature based on selecting the entire face as input to the fake detection system, and (ii) a novel approach based on the selection of specific facial regions as input to the fake detection system. Fusion techniques are applied both to the facial regions and also to three different state-of-the-art fake detection systems (Xception, Capsule Network, and DSP-FWA) in order to further increase the robustness of the detectors considered. Finally, experiments regarding intra- and inter-database scenarios are performed. Among all the findings resulting from our experiments, we highlight: (i) the very good results achieved using facial regions and fusion techniques with fake detection results above 99% Area Under the Curve (AUC) for UADFV, FaceForensics++, and Celeb-DF v2 databases, and (ii) the necessity to put more efforts on the analysis of inter-database scenarios to improve the ability of the fake detectors against attacks unseen during learningThis work has been supported by projects: PRIMA (H2020-MSCAITN-2019-860315), TRESPASS-ETN (H2020-MSCA-ITN-2019-860813), BIBECA, Spain (MINECO/FEDER RTI2018-101248-B-I00)ElsevierDepartamento de Tecnología Electrónica y de las ComunicacionesEscuela Politécnica Superior20222022-04-01research articlehttp://purl.org/coar/resource_type/c_2df8fbb1VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10486/702775https://dx.doi.org/10.1016/j.engappai.2022.104673reponame:Biblos-e Archivo. Repositorio Institucional de la UAMinstname:Universidad Autónoma de MadridInglésengEuropean Commission http://dx.doi.org/10.13039/501100000780 Horizon 2020 Framework Programme 860315European Commission http://dx.doi.org/10.13039/501100000780 Horizon 2020 Framework Programme 860813open accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:repositorio.uam.es:10486/7027752026-06-23T12:46:27Z
dc.title.none.fl_str_mv DeepFakes detection across generations: Analysis of facial regions, fusion, and performance evaluation
title DeepFakes detection across generations: Analysis of facial regions, fusion, and performance evaluation
spellingShingle DeepFakes detection across generations: Analysis of facial regions, fusion, and performance evaluation
Tolosana Moranchel, Rubén
Benchmark
Databases
DeepFakes
Face manipulation
Fake detection
Fake news
Media forensics
Telecomunicaciones
title_short DeepFakes detection across generations: Analysis of facial regions, fusion, and performance evaluation
title_full DeepFakes detection across generations: Analysis of facial regions, fusion, and performance evaluation
title_fullStr DeepFakes detection across generations: Analysis of facial regions, fusion, and performance evaluation
title_full_unstemmed DeepFakes detection across generations: Analysis of facial regions, fusion, and performance evaluation
title_sort DeepFakes detection across generations: Analysis of facial regions, fusion, and performance evaluation
dc.creator.none.fl_str_mv Tolosana Moranchel, Rubén
Romero Tapiador, Sergio
Gonzalez Sosa
Vera Rodríguez, Rubén
Fiérrez Aguilar, Julián
author Tolosana Moranchel, Rubén
author_facet Tolosana Moranchel, Rubén
Romero Tapiador, Sergio
Gonzalez Sosa
Vera Rodríguez, Rubén
Fiérrez Aguilar, Julián
author_role author
author2 Romero Tapiador, Sergio
Gonzalez Sosa
Vera Rodríguez, Rubén
Fiérrez Aguilar, Julián
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Departamento de Tecnología Electrónica y de las Comunicaciones
Escuela Politécnica Superior
dc.subject.none.fl_str_mv Benchmark
Databases
DeepFakes
Face manipulation
Fake detection
Fake news
Media forensics
Telecomunicaciones
topic Benchmark
Databases
DeepFakes
Face manipulation
Fake detection
Fake news
Media forensics
Telecomunicaciones
description Media forensics has attracted a tremendous attention in the last years in part due to the increasing concerns around DeepFakes. Since the release of the initial DeepFakes databases of the 1st generation such as UADFV and FaceForensics++ up to the latest databases of the 2nd generation such as Celeb-DF and DFDC, many visual improvements have been carried out, making fake videos almost indistinguishable to the human eye. This study provides an in-depth analysis of both 1st and 2nd DeepFakes generations in terms of fake detection performance. Two different methods are considered in our experimental framework: (i) the traditional one followed in the literature based on selecting the entire face as input to the fake detection system, and (ii) a novel approach based on the selection of specific facial regions as input to the fake detection system. Fusion techniques are applied both to the facial regions and also to three different state-of-the-art fake detection systems (Xception, Capsule Network, and DSP-FWA) in order to further increase the robustness of the detectors considered. Finally, experiments regarding intra- and inter-database scenarios are performed. Among all the findings resulting from our experiments, we highlight: (i) the very good results achieved using facial regions and fusion techniques with fake detection results above 99% Area Under the Curve (AUC) for UADFV, FaceForensics++, and Celeb-DF v2 databases, and (ii) the necessity to put more efforts on the analysis of inter-database scenarios to improve the ability of the fake detectors against attacks unseen during learning
publishDate 2022
dc.date.none.fl_str_mv 2022
2022-04-01
dc.type.none.fl_str_mv research article
http://purl.org/coar/resource_type/c_2df8fbb1
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10486/702775
https://dx.doi.org/10.1016/j.engappai.2022.104673
url http://hdl.handle.net/10486/702775
https://dx.doi.org/10.1016/j.engappai.2022.104673
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv European Commission http://dx.doi.org/10.13039/501100000780 Horizon 2020 Framework Programme 860315
European Commission http://dx.doi.org/10.13039/501100000780 Horizon 2020 Framework Programme 860813

dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:Biblos-e Archivo. Repositorio Institucional de la UAM
instname:Universidad Autónoma de Madrid
instname_str Universidad Autónoma de Madrid
reponame_str Biblos-e Archivo. Repositorio Institucional de la UAM
collection Biblos-e Archivo. Repositorio Institucional de la UAM
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869415186566217728
score 15.300724