Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection

Although current deep learning-based face forgery detectors achieve impressive performance in constrained scenarios, they are vulnerable to samples created by unseen manipulation methods. Some recent works show improvements in generalisation but rely on cues that are easily corrupted by common post-...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 5037 - 5047
Hlavní autoři: Haliassos, Alexandros, Vougioukas, Konstantinos, Petridis, Stavros, Pantic, Maja
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2021
Témata:
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Although current deep learning-based face forgery detectors achieve impressive performance in constrained scenarios, they are vulnerable to samples created by unseen manipulation methods. Some recent works show improvements in generalisation but rely on cues that are easily corrupted by common post-processing operations such as compression. In this paper, we propose LipForensics, a detection approach capable of both generalising to novel manipulations and withstanding various distortions. LipForensics targets high-level semantic irregularities in mouth movements, which are common in many generated videos. It consists in first pretraining a spatio-temporal network to perform visual speech recognition (lipreading), thus learning rich internal representations related to natural mouth motion. A temporal network is subsequently finetuned on fixed mouth embeddings of real and forged data in order to detect fake videos based on mouth movements without overfitting to low-level, manipulation-specific artefacts. Extensive experiments show that this simple approach significantly surpasses the state-of-the-art in terms of generalisation to unseen manipulations and robustness to perturbations, as well as shed light on the factors responsible for its performance.
AbstractList Although current deep learning-based face forgery detectors achieve impressive performance in constrained scenarios, they are vulnerable to samples created by unseen manipulation methods. Some recent works show improvements in generalisation but rely on cues that are easily corrupted by common post-processing operations such as compression. In this paper, we propose LipForensics, a detection approach capable of both generalising to novel manipulations and withstanding various distortions. LipForensics targets high-level semantic irregularities in mouth movements, which are common in many generated videos. It consists in first pretraining a spatio-temporal network to perform visual speech recognition (lipreading), thus learning rich internal representations related to natural mouth motion. A temporal network is subsequently finetuned on fixed mouth embeddings of real and forged data in order to detect fake videos based on mouth movements without overfitting to low-level, manipulation-specific artefacts. Extensive experiments show that this simple approach significantly surpasses the state-of-the-art in terms of generalisation to unseen manipulations and robustness to perturbations, as well as shed light on the factors responsible for its performance.
Author Vougioukas, Konstantinos
Petridis, Stavros
Haliassos, Alexandros
Pantic, Maja
Author_xml – sequence: 1
  givenname: Alexandros
  surname: Haliassos
  fullname: Haliassos, Alexandros
  email: alexandros.haliassos14@imperial.ac.uk
  organization: Imperial College London
– sequence: 2
  givenname: Konstantinos
  surname: Vougioukas
  fullname: Vougioukas, Konstantinos
  email: k.vougioukas@imperial.ac.uk
  organization: Imperial College London
– sequence: 3
  givenname: Stavros
  surname: Petridis
  fullname: Petridis, Stavros
  email: stavros.petridis04@imperial.ac.uk
  organization: Imperial College London
– sequence: 4
  givenname: Maja
  surname: Pantic
  fullname: Pantic, Maja
  email: m.pantic@imperial.ac.uk
  organization: Imperial College London
BookMark eNotzLFOwzAUQFGDQKIt_QIYvDGlvGfHdsxWtbQgBYEqYK0c5xmMQhwl6dC_BwmmO507ZWdtaomxa4QFItjb1fvLLte5NAsBAhcACuCETVFrlecKrDhlEwQtM23RXrD5MHwBgBSI2hYT9lTGbuDr1N6MvIx0x5d8Sy31romDqxrirq35LlWHYeTLruuT8598THzjPPFN6j-oP_I1jeTHmNpLdh5cM9D8vzP2trl_XT1k5fP2cbUssyhAjpm0TtZkAipjbBEK6Wr0AmUQVai0B_KkTKEFaFUobQyS9igKGYwKdfAoZ-zq7xuJaN_18dv1x739RRZB_gDFSU7l
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR46437.2021.00500
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 1665445092
9781665445092
EISSN 1063-6919
EndPage 5047
ExternalDocumentID 9578910
Genre orig-research
GroupedDBID 6IE
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i203t-39a3de7f157798f83ad1c213f2bfb6c0ece57862065856771e6c1283f75fdfc13
IEDL.DBID RIE
ISICitedReferencesCount 321
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000739917305024&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:28:29 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-39a3de7f157798f83ad1c213f2bfb6c0ece57862065856771e6c1283f75fdfc13
PageCount 11
ParticipantIDs ieee_primary_9578910
PublicationCentury 2000
PublicationDate 2021-June
PublicationDateYYYYMMDD 2021-06-01
PublicationDate_xml – month: 06
  year: 2021
  text: 2021-June
PublicationDecade 2020
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationYear 2021
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
Score 2.6587799
Snippet Although current deep learning-based face forgery detectors achieve impressive performance in constrained scenarios, they are vulnerable to samples created by...
SourceID ieee
SourceType Publisher
StartPage 5037
SubjectTerms Face recognition
Meetings
Mouth
Perturbation methods
Semantics
Speech recognition
Visualization
Title Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection
URI https://ieeexplore.ieee.org/document/9578910
WOSCitedRecordID wos000739917305024&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFA9zePDkxyZ-k4PgxW5N0iaNt7FZPMwxhspuo0leoCDtWDv_fpOuTAQv3kIuebwkvM_f7yF0H8VZIhNuAuASgkhpFmTShoGgsQWiFSWmmVoyFbNZslzKeQc97rEwANA0n8HAL5tavin11qfKhtI9L-nxVAdCiB1Wa59PYS6S4TJp0XEklMPxx3wR-bqUiwIpGXimk_DXDJXGhKTH_zv8BPV_sHh4vrcyp6gDxRk6bp1H3H7Nqodep_m6wpOyeKjxNIcnPMItpbRn0f0EnBUGL0q1rWo8aonEcV3iNHMHpGUDjsYTqJvWrKKP3tPnt_FL0M5KCHIasjpgMmMGhCWxEDKxCcsM0ZQwS5VVXIegwcnPqfc4Yi4EAa6daWJWxNZYTdg56hZlARcIJ1rGRhOIQgtRBlQKJ4hWyjoPl0sVXqKe185qvaPDWLWKufp7-xodefXvuqtuULfebOEWHeqvOq82d80dfgNitp0d
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fS8MwEA5jCvo0dRN_mwfBF7s1SZs0vo3NMbEbY0zZ22jTCxSkHWvn32_SlYngi28hL3fcJdxdct93CD14fhTIgCcOcAmOFyvmRFK7jqC-BqJiSpJqakkoptNguZSzBnraY2EAoGo-g65dVn_5Sa629qmsJ83xkhZPdeB7HiU7tNb-RYWZWobLoMbHEVf2Bh-zuWd_pkwdSEnXcp24v6aoVEFk1Pqf-BPU-UHj4dk-zpyiBmRnqFWnj7i-nEUbTcJ0XeBhnj2WOEzhGfdxTSpteXQ_AUdZgud5vC1K3K-pxHGZ41FkBIzyCh6Nh1BWzVlZB72PXhaDsVNPS3BS6rLSYTJiCQhNfCFkoAMWJURRwjSNdcyVCwqM_pzanMPnQhDgygQnpoWvE60IO0fNLM_gAuFAST9RBDxXgxcBlcIoouJYmxyXy9i9RG1rndV6R4ixqg1z9ff2PToaLybhKnydvl2jY-uKXa_VDWqWmy3cokP1VabF5q7y5ze_kKBk
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=Lips+Don%27t+Lie%3A+A+Generalisable+and+Robust+Approach+to+Face+Forgery+Detection&rft.au=Haliassos%2C+Alexandros&rft.au=Vougioukas%2C+Konstantinos&rft.au=Petridis%2C+Stavros&rft.au=Pantic%2C+Maja&rft.date=2021-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=5037&rft.epage=5047&rft_id=info:doi/10.1109%2FCVPR46437.2021.00500&rft.externalDocID=9578910