View in EDS HTML Full Text PDF Full Text

Robust Sequential DeepFake Detection.

Saved in:
Bibliographic Details
Title: Robust Sequential DeepFake Detection.
Authors: Shao, Rui1 (AUTHOR) shaorui@hit.edu.cn, Wu, Tianxing2 (AUTHOR) twu012@ntu.edu.sg, Liu, Ziwei2 (AUTHOR) ziwei.liu@ntu.edu.sg
Source: International Journal of Computer Vision. Jun2025, Vol. 133 Issue 6, p3278-3295. 18p.
Subjects: Sequential learning, Artificial intelligence, Image processing, Motivation (Psychology), Annotations
Abstract: Since photorealistic faces can be readily generated by facial manipulation technologies nowadays, potential malicious abuse of these technologies has drawn great concerns. Numerous deepfake detection methods are thus proposed. However, existing methods only focus on detecting one-step facial manipulation. As the emergence of easy-accessible facial editing applications, people can easily manipulate facial components using multi-step operations in a sequential manner. This new threat requires us to detect a sequence of facial manipulations, which is vital for both detecting deepfake media and recovering original faces afterwards. Motivated by this observation, we emphasize the need and propose a novel research problem called Detecting Sequential DeepFake Manipulation (Seq-DeepFake). Unlike the existing deepfake detection task only demanding a binary label prediction, detecting Seq-DeepFake manipulation requires correctly predicting a sequential vector of facial manipulation operations. To support a large-scale investigation, we construct the first Seq-DeepFake dataset, where face images are manipulated sequentially with corresponding annotations of sequential facial manipulation vectors. Based on this new dataset, we cast detecting Seq-DeepFake manipulation as a specific image-to-sequence (e.g., image captioning) task and propose a concise yet effective Seq-DeepFake Transformer (SeqFakeFormer). To better reflect real-world deepfake data distributions, we further apply various perturbations on the original Seq-DeepFake dataset and construct the more challenging Sequential DeepFake dataset with perturbations (Seq-DeepFake-P). To exploit deeper correlation between images and sequences when facing Seq-DeepFake-P, a dedicated Seq-DeepFake Transformer with Image-Sequence Reasoning (SeqFakeFormer++) is devised, which builds stronger correspondence between image-sequence pairs for more robust Seq-DeepFake detection. Moreover, we build a comprehensive benchmark and set up rigorous evaluation protocols and metrics for this new research problem. Extensive quantitative and qualitative experiments demonstrate the effectiveness of SeqFakeFormer and SeqFakeFormer++. Several valuable observations are also revealed to facilitate future research in broader deepfake detection problems. The code has been released at https://github.com/rshaojimmy/SeqDeepFake/. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Computer Vision is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 185069261
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Robust Sequential DeepFake Detection.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Shao%2C+Rui%22">Shao, Rui</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> shaorui@hit.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Wu%2C+Tianxing%22">Wu, Tianxing</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> twu012@ntu.edu.sg</i><br /><searchLink fieldCode="AR" term="%22Liu%2C+Ziwei%22">Liu, Ziwei</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> ziwei.liu@ntu.edu.sg</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Computer+Vision%22">International Journal of Computer Vision</searchLink>. Jun2025, Vol. 133 Issue 6, p3278-3295. 18p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Sequential+learning%22">Sequential learning</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Image+processing%22">Image processing</searchLink><br /><searchLink fieldCode="DE" term="%22Motivation+%28Psychology%29%22">Motivation (Psychology)</searchLink><br /><searchLink fieldCode="DE" term="%22Annotations%22">Annotations</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Since photorealistic faces can be readily generated by facial manipulation technologies nowadays, potential malicious abuse of these technologies has drawn great concerns. Numerous deepfake detection methods are thus proposed. However, existing methods only focus on detecting one-step facial manipulation. As the emergence of easy-accessible facial editing applications, people can easily manipulate facial components using multi-step operations in a sequential manner. This new threat requires us to detect a sequence of facial manipulations, which is vital for both detecting deepfake media and recovering original faces afterwards. Motivated by this observation, we emphasize the need and propose a novel research problem called Detecting Sequential DeepFake Manipulation (Seq-DeepFake). Unlike the existing deepfake detection task only demanding a binary label prediction, detecting Seq-DeepFake manipulation requires correctly predicting a sequential vector of facial manipulation operations. To support a large-scale investigation, we construct the first Seq-DeepFake dataset, where face images are manipulated sequentially with corresponding annotations of sequential facial manipulation vectors. Based on this new dataset, we cast detecting Seq-DeepFake manipulation as a specific image-to-sequence (e.g., image captioning) task and propose a concise yet effective Seq-DeepFake Transformer (SeqFakeFormer). To better reflect real-world deepfake data distributions, we further apply various perturbations on the original Seq-DeepFake dataset and construct the more challenging Sequential DeepFake dataset with perturbations (Seq-DeepFake-P). To exploit deeper correlation between images and sequences when facing Seq-DeepFake-P, a dedicated Seq-DeepFake Transformer with Image-Sequence Reasoning (SeqFakeFormer++) is devised, which builds stronger correspondence between image-sequence pairs for more robust Seq-DeepFake detection. Moreover, we build a comprehensive benchmark and set up rigorous evaluation protocols and metrics for this new research problem. Extensive quantitative and qualitative experiments demonstrate the effectiveness of SeqFakeFormer and SeqFakeFormer++. Several valuable observations are also revealed to facilitate future research in broader deepfake detection problems. The code has been released at https://github.com/rshaojimmy/SeqDeepFake/. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of International Journal of Computer Vision is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=185069261
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s11263-024-02339-6
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 18
        StartPage: 3278
    Subjects:
      – SubjectFull: Sequential learning
        Type: general
      – SubjectFull: Artificial intelligence
        Type: general
      – SubjectFull: Image processing
        Type: general
      – SubjectFull: Motivation (Psychology)
        Type: general
      – SubjectFull: Annotations
        Type: general
    Titles:
      – TitleFull: Robust Sequential DeepFake Detection.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Shao, Rui
      – PersonEntity:
          Name:
            NameFull: Wu, Tianxing
      – PersonEntity:
          Name:
            NameFull: Liu, Ziwei
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 09205691
          Numbering:
            – Type: volume
              Value: 133
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: International Journal of Computer Vision
              Type: main
ResultId 1