Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics

AI-synthesized face-swapping videos, commonly known as DeepFakes, is an emerging problem threatening the trustworthiness of online information. The need to develop and evaluate DeepFake detection algorithms calls for datasets of DeepFake videos. However, current DeepFake datasets suffer from low vis...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 3204 - 3213
Hlavní autori: Li, Yuezun, Yang, Xin, Sun, Pu, Qi, Honggang, Lyu, Siwei
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.06.2020
Predmet:
ISSN:1063-6919
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract AI-synthesized face-swapping videos, commonly known as DeepFakes, is an emerging problem threatening the trustworthiness of online information. The need to develop and evaluate DeepFake detection algorithms calls for datasets of DeepFake videos. However, current DeepFake datasets suffer from low visual quality and do not resemble DeepFake videos circulated on the Internet. We present a new large-scale challenging DeepFake video dataset, Celeb-DF, which contains 5,639 high-quality DeepFake videos of celebrities generated using improved synthesis process. We conduct a comprehensive evaluation of DeepFake detection methods and datasets to demonstrate the escalated level of challenges posed by Celeb-DF.
AbstractList AI-synthesized face-swapping videos, commonly known as DeepFakes, is an emerging problem threatening the trustworthiness of online information. The need to develop and evaluate DeepFake detection algorithms calls for datasets of DeepFake videos. However, current DeepFake datasets suffer from low visual quality and do not resemble DeepFake videos circulated on the Internet. We present a new large-scale challenging DeepFake video dataset, Celeb-DF, which contains 5,639 high-quality DeepFake videos of celebrities generated using improved synthesis process. We conduct a comprehensive evaluation of DeepFake detection methods and datasets to demonstrate the escalated level of challenges posed by Celeb-DF.
Author Li, Yuezun
Yang, Xin
Sun, Pu
Qi, Honggang
Lyu, Siwei
Author_xml – sequence: 1
  givenname: Yuezun
  surname: Li
  fullname: Li, Yuezun
  organization: University at Albany, State University of New York, USA
– sequence: 2
  givenname: Xin
  surname: Yang
  fullname: Yang, Xin
  organization: University at Albany, State University of New York, USA
– sequence: 3
  givenname: Pu
  surname: Sun
  fullname: Sun, Pu
  organization: University of Chinese Academy of Sciences, China
– sequence: 4
  givenname: Honggang
  surname: Qi
  fullname: Qi, Honggang
  organization: University of Chinese Academy of Sciences, China
– sequence: 5
  givenname: Siwei
  surname: Lyu
  fullname: Lyu, Siwei
  organization: University at Albany, State University of New York, USA
BookMark eNotjMtOwzAQAA0CiVLyBXDwD6Ts2vHa5lZSAkiVQLyulRuvQyCkVdILf18QHEZzGc2pOOo3PQtxgTBDBH9Zvj0-FYoAZgoUzAC0sgci89ahVT8gOXMoJgikc_LoT0Q2jh_w2yGSdxNxXXLH63xRXcm5XIah4fy5Dh3L8j10HfdN2zdyEXZh5J1Mm0EumLdV-GRZbQbux7Yez8RxCt3I2b-n4rW6eSnv8uXD7X05X-atAr3LEyUIWploULFR0TmTtFoXFMk6b70yENEyeJ1izTUVxtkCAsWIiAUlPRXnf9-WmVfbof0Kw_fKoyFNTu8BTqtKuQ
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR42600.2020.00327
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/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 9781728171685
1728171687
EISSN 1063-6919
EndPage 3213
ExternalDocumentID 9156368
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-f6f0a325d512e52d885f32b46d678979250d17e093fdcec6458740a6dd11146f3
IEDL.DBID RIE
ISICitedReferencesCount 1050
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000620679503046&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 02:30:35 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-f6f0a325d512e52d885f32b46d678979250d17e093fdcec6458740a6dd11146f3
PageCount 10
ParticipantIDs ieee_primary_9156368
PublicationCentury 2000
PublicationDate 2020-Jun
PublicationDateYYYYMMDD 2020-06-01
PublicationDate_xml – month: 06
  year: 2020
  text: 2020-Jun
PublicationDecade 2020
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationYear 2020
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
Score 2.6552546
Snippet AI-synthesized face-swapping videos, commonly known as DeepFakes, is an emerging problem threatening the trustworthiness of online information. The need to...
SourceID ieee
SourceType Publisher
StartPage 3204
SubjectTerms Decoding
Detection algorithms
Image color analysis
Training
Videos
Visualization
YouTube
Title Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics
URI https://ieeexplore.ieee.org/document/9156368
WOSCitedRecordID wos000620679503046&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/eLvHCXMwlV1LSwMxEA5t8eCpaiu-ycGjsbubzcubti4epBRf9FaymwkUYVvarb_fyXapCF68hUAIzBC-mcl88xFyjaCXKw0xE0YoloKSzETeM4wdCqk9ooS1tdiEGo_1dGomLXKz48IAQN18BrdhWf_lu0WxCaWygcFkg0vdJm2l1JartauncMxkpNENOy6OzGD4MXmp569jFpiEBi6e_NZQqSEk6_7v8gPS_-Hi0ckOZQ5JC8oj0m2CR9o8zXWPPAwRQHI2yu7oPX0O_d3sFe0PdNjIpeBpOrIVolZFMVKlI4BlZj-BBnXOEp217pP37PFt-MQagQQ2TyJeMS99ZHkiHKI2iMRpLTxP8lQ6hCCjDIY3LlYQGe5dAYVMRRDgs9K5OJCRPT8mnXJRwgmhhYjAC-u1VZCCl9bhqSTXcRqms8TpKekFk8yW2xkYs8YaZ39vn5P9YPNtS9UF6VSrDVySveKrmq9XV7XjvgFq95aW
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NSwMxEA21Cnqq2orf5uDR2N1skk286dalYi1Fq_RW0s0EirAt7dbfb7JdKoIXbyEQAjOENzOZNw-hawd6k1hCSLjiMWEQC6ICa4mLHTIhrUMJrUuxibjfl6ORGtTQzYYLAwBl8xnc-mX5l29m2cqXytrKJRuRkFtomzNGwzVba1NRiVwuI5Ss-HFhoNrJx-C1nMDu8kDqW7gi-ltFpQSRtPG_6_dR64eNhwcbnDlANcgPUaMKH3H1OJdN9JA4CJmQTnqH73HPd3iTN-cBwEklmOJO444uHG4V2MWquAMwT_UnYK_PmTt3LVvoPX0cJl1SSSSQKQ2iglhhAx1RbhxuA6dGSm4jOmHCOBBSsXIBjgljCFRkTQaZYNxL8GlhTOjpyDY6QvV8lsMxwhkPwHJtpY6BgRXauFN0IkPm57OE7AQ1vUnG8_UUjHFljdO_t6_Qbnf40hv3nvrPZ2jP23_dYHWO6sViBRdoJ_sqpsvFZenEb3Qmmd0
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%3Abook&rft.genre=proceeding&rft.title=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=Celeb-DF%3A+A+Large-Scale+Challenging+Dataset+for+DeepFake+Forensics&rft.au=Li%2C+Yuezun&rft.au=Yang%2C+Xin&rft.au=Sun%2C+Pu&rft.au=Qi%2C+Honggang&rft.date=2020-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=3204&rft.epage=3213&rft_id=info:doi/10.1109%2FCVPR42600.2020.00327&rft.externalDocID=9156368