DF-Platter: Multi-Face Heterogeneous Deepfake Dataset

Deepfake detection is gaining significant importance in the research community. While most of the research efforts are focused towards high-quality images and videos with controlled appearance of individuals, deepfake generation algorithms now have the capability to generate deep-fakes with low-reso...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 9739 - 9748
Hlavní autori: Narayan, Kartik, Agarwal, Harsh, Thakral, Kartik, Mittal, Surbhi, Vatsa, Mayank, Singh, Richa
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.06.2023
Predmet:
Benchmark testing
Computer vision
Datasets and evaluation
Deepfakes
Face recognition
Image coding
Skin
ISSN:1063-6919
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Deepfake detection is gaining significant importance in the research community. While most of the research efforts are focused towards high-quality images and videos with controlled appearance of individuals, deepfake generation algorithms now have the capability to generate deep-fakes with low-resolution, occlusion, and manipulation of multiple subjects. In this research, we emulate the real-world scenario of deepfake generation and propose the DF-Platter dataset, which contains (i) both low-resolution and high-resolution deepfakes generated using multiple generation techniques and (ii) single-subject and multiple-subject deepfakes, with face images of Indian ethnicity. Faces in the dataset are annotated for various attributes such as gender, age, skin tone, and occlusion. The dataset is prepared in 116 days with continuous usage of 32 GPUs accounting to 1,800 GB cumulative memory. With over 500 GBs in size, the dataset contains a total of 133,260 videos encompassing three sets. To the best of our knowledge, this is one of the largest datasets containing vast variability and multiple challenges. We also provide benchmark results under multiple evaluation settings using popular and state-of-the-art deepfake detection models, for c0 images and videos along with c23 and c40 compression variants. The results demonstrate a significant performance reduction in the deepfake detection task on low-resolution deep-fakes. Furthermore, existing techniques yield declined detection accuracy on multiple-subject deepfakes. It is our assertion that this database will improve the state-of-the-art by extending the capabilities of deepfake detection algorithms to real-world scenarios. The database is available at: http://iab-rubric.org/df-platter-database.
AbstractList Deepfake detection is gaining significant importance in the research community. While most of the research efforts are focused towards high-quality images and videos with controlled appearance of individuals, deepfake generation algorithms now have the capability to generate deep-fakes with low-resolution, occlusion, and manipulation of multiple subjects. In this research, we emulate the real-world scenario of deepfake generation and propose the DF-Platter dataset, which contains (i) both low-resolution and high-resolution deepfakes generated using multiple generation techniques and (ii) single-subject and multiple-subject deepfakes, with face images of Indian ethnicity. Faces in the dataset are annotated for various attributes such as gender, age, skin tone, and occlusion. The dataset is prepared in 116 days with continuous usage of 32 GPUs accounting to 1,800 GB cumulative memory. With over 500 GBs in size, the dataset contains a total of 133,260 videos encompassing three sets. To the best of our knowledge, this is one of the largest datasets containing vast variability and multiple challenges. We also provide benchmark results under multiple evaluation settings using popular and state-of-the-art deepfake detection models, for c0 images and videos along with c23 and c40 compression variants. The results demonstrate a significant performance reduction in the deepfake detection task on low-resolution deep-fakes. Furthermore, existing techniques yield declined detection accuracy on multiple-subject deepfakes. It is our assertion that this database will improve the state-of-the-art by extending the capabilities of deepfake detection algorithms to real-world scenarios. The database is available at: http://iab-rubric.org/df-platter-database.
Author Narayan, Kartik
Singh, Richa
Vatsa, Mayank
Thakral, Kartik
Agarwal, Harsh
Mittal, Surbhi
Author_xml – sequence: 1
  givenname: Kartik
  surname: Narayan
  fullname: Narayan, Kartik
  email: narayan.2@iitj.ac.in
  organization: IIT Jodhpur,India
– sequence: 2
  givenname: Harsh
  surname: Agarwal
  fullname: Agarwal, Harsh
  email: agarwal.10@iitj.ac.in
  organization: IIT Jodhpur,India
– sequence: 3
  givenname: Kartik
  surname: Thakral
  fullname: Thakral, Kartik
  email: thakral.1@iitj.ac.in
  organization: IIT Jodhpur,India
– sequence: 4
  givenname: Surbhi
  surname: Mittal
  fullname: Mittal, Surbhi
  email: mittal.5@iitj.ac.in
  organization: IIT Jodhpur,India
– sequence: 5
  givenname: Mayank
  surname: Vatsa
  fullname: Vatsa, Mayank
  email: mvatsa@iitj.ac.in
  organization: IIT Jodhpur,India
– sequence: 6
  givenname: Richa
  surname: Singh
  fullname: Singh, Richa
  email: richa@iitj.ac.in
  organization: IIT Jodhpur,India
BookMark eNotzM1Kw0AUQOFRFKw1b9BFXiDxztzJ_LiT1FihYhF1W27SOxKNSUmmC9--BV0dOIvvWlz0Q89CLCTkUoK_LT82r4WyyucKFOYAHv2ZSLz1DgtAkMq7czGTYDAzXvorkUzTFwCgktJ4NxPFsso2HcXI4136fOhim1XUcLri0xk-uefhMKVL5n2gb06XFGnieCMuA3UTJ_-di_fq4a1cZeuXx6fyfp21CnTMjEIk0s3Osnc7smSLQIYaNKEIQRujiJTVxrLhgmoyLmBdIwYpKWjtcC4Wf27LzNv92P7Q-LuVcNKt1HgESmpIiA
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR52729.2023.00939
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 9798350301298
EISSN 1063-6919
EndPage 9748
ExternalDocumentID 10204714
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-i204t-6233aa4cd7e98da7a75fa6ac36f5ff4662aa27467e6e5aba68f3bb33f11af4483
IEDL.DBID RIE
ISICitedReferencesCount 32
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001062522102005&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 02:56:30 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i204t-6233aa4cd7e98da7a75fa6ac36f5ff4662aa27467e6e5aba68f3bb33f11af4483
PageCount 10
ParticipantIDs ieee_primary_10204714
PublicationCentury 2000
PublicationDate 2023-June
PublicationDateYYYYMMDD 2023-06-01
PublicationDate_xml – month: 06
  year: 2023
  text: 2023-June
PublicationDecade 2020
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationYear 2023
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
Score 2.4885514
Snippet Deepfake detection is gaining significant importance in the research community. While most of the research efforts are focused towards high-quality images and...
SourceID ieee
SourceType Publisher
StartPage 9739
SubjectTerms Benchmark testing
Computer vision
Datasets and evaluation
Deepfakes
Face recognition
Image coding
Skin
Title DF-Platter: Multi-Face Heterogeneous Deepfake Dataset
URI https://ieeexplore.ieee.org/document/10204714
WOSCitedRecordID wos001062522102005&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/eLvHCXMwlV09T8MwED3RioGpfBTxrQysLk2c2DFrS9QBVREC1K06O2epArVVm_L7sZ0AYmBgsyJZls6-3D373j2A24TQN_lOmcmMAyjCep-riLlUBCWvtM4b1ZJHOZ3ms5kqW7J64MIQUSg-o4Efhrf8amV2_qrMeXgydD_TtAMdKUVD1vq-UOEOygiVt_S4eKjuRq_lU5a47HHgNcIHHryrXyIqIYYUvX-ufgj9HzZeVH7HmSPYo-Ux9Nr0MWqdc3sC2bhg5Xvol3kfBWItK9DNnfiKl5U7KORQfjQmWlt8o2iMtYtgdR9eiofn0YS1qghs4davmctXOGJqKkkqr1CizCwKNFzYzNpUiAQx8SIiJChDjSK3XGvObRyjdWCMn0J3uVrSGURk_LOl8WRqmSpD2lQitji0mqTSuTmHvjfDfN00vph_WeDij--XcOAt3VRSXUG33uzoGvbNR73Ybm7Cdn0CQaiVog
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT8MwDLVgIMFpfAzxTQ9cM9qmTVuuG9UQY6rQQLtNTupIE2idto7fT9KWIQ4cuEWVokhOXPslfn4Atz6hbfIdMBUqA1CEtj6XEzOpCEY8lzKuVUuG0WgUTyZJ1pDVKy4MEVXFZ9S1w-otPy_U2l6VGQ_3XfMzDbZhJwwC363pWpsrFW7AjEjihiDnucld7y17CX2TP3atSnjXwvfkl4xKFUXS9j_XP4DODx_PyTaR5hC2aH4E7SaBdBr3XB1D2E9Z9lF1zLx3KmotS9HMHdial8IcFTI43-kTLTS-k9PH0sSwsgOv6cO4N2CNLgKbmfVLZjIWjhioPKIkzjHCKNQoUHGhQ60DIXxE38qIkKAQJYpYcyk5156H2sAxfgKteTGnU3BI2YdLZenUUZAokioXnkZXS4oSGasz6FgzTBd164vptwXO__h-A3uD8fNwOnwcPV3AvrV6XVd1Ca1yuaYr2FWf5Wy1vK627gs8d5jp
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=DF-Platter%3A+Multi-Face+Heterogeneous+Deepfake+Dataset&rft.au=Narayan%2C+Kartik&rft.au=Agarwal%2C+Harsh&rft.au=Thakral%2C+Kartik&rft.au=Mittal%2C+Surbhi&rft.date=2023-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=9739&rft.epage=9748&rft_id=info:doi/10.1109%2FCVPR52729.2023.00939&rft.externalDocID=10204714