CoChat

Implicit Identity Driven Deepfake Face Swapping Detection

Huang, Baojin, Wang, Zhongyuan, Yang, Jifan, Ai, Jiaxin, Zou, Qin, Wang, Qian, Ye, Dengpan · 2023 · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Cited by 172

The DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.

Abstract

In this paper, we consider the face swapping detection from the perspective of face identity. Face swapping aims to replace the target face with the source face and generate the fake face that the human cannot distinguish between real and fake. We argue that the fake face contains the explicit identity and implicit identity, which respectively corresponds to the identity of the source face and target face during face swapping. Note that the explicit identities of faces can be extracted by regular face recognizers. Particularly, the implicit identity of real face is consistent with the its explicit identity. Thus the difference between explicit and implicit identity of face facilitates face swapping detection. Following this idea, we propose a novel implicit identity driven framework for face swapping detection. Specifically, we design an explicit identity contrast (EIC) loss and an implicit identity exploration (IIE) loss, which supervises a CNN backbone to embed face images into the implicit identity space. Under the guidance of EIC, real samples are pulled closer to their explicit identities, while fake samples are pushed away from their explicit identities. More-over, IIE is derived from the margin-based classification loss function, which encourages the fake faces with known target identities to enjoy intra-class compactness and inter-class diversity. Extensive experiments and visualizations on several datasets demonstrate the generalization of our method against the state-of-the-art counterparts.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr52729.2023.00436

Cites

35 of 35 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 21

  1. 10.1109/CVPR.2018.00702 · DOI · Paper page
  2. 10.1145/3474085.3475347 · DOI
  3. Cozzolino, 2018, Forensic transfer: Weakly-supervised domain adaptation for forgery detection, arXiv preprint
  4. Deng, 2019, Retinaface: Single-stage dense face localisation in the wild, arXiv: Computer Vision and Pattern Recognition
  5. 10.1109/CVPR46437.2021.00341 · DOI · Paper page
  6. 10.1109/CVPR46437.2021.01585 · DOI · Paper page
  7. 2017, Deepfakes
  8. 2017, Faceswap
  9. 10.1609/aaai.v36i1.19954 · DOI · Paper page
  10. Zhihao, 2021, Spatiotemporal in consistency learning for deepfake video detection, 3473
  11. 10.1109/CVPR42600.2020.00594 · DOI · Paper page
  12. 10.1609/aaai.v32i1.11596 · DOI · Paper page
  13. Li, 2019, Faceshifter: Towards high fidelity and occlusion aware face swapping, arXiv preprint
  14. 10.1007/978-3-030-20876-9_8 · DOI · Paper page
  15. Dufour, 2019, Deep fake detection dataset
  16. 10.2307/j.ctvcm4g18.8 · DOI · Paper page
  17. Simonyan, 2014, Very deep convolutional networks for large-scale image recognition, arXiv preprint
  18. Ke, 2022, An information theoretic approach for attention-driven face forgery detection, 111
  19. 10.1145/3306346.3323035 · DOI · Paper page
  20. 10.1609/aaai.v34i07.6916 · DOI · Paper page
  21. 10.1007/978-3-031-20065-6_23 · DOI

Cited by

See all 172

Metadata

Authors
Huang, B., Wang, Z., Yang, J., Ai, J., Zou, Q., Wang, Q., & Ye, D.
Venue
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2023-06
Pages
4490-4499
ISSN
1063-6919 (ISSN-L)
OpenAlex
W4386065949
Cited by
172
References
35
FWCI
19.56
Type
conference paper
Language
en
Open access
closed
Funders
  • National Key Research and Development Program of China (YFF0602102)
  • National Natural Science Foundation of China (U1903214,62171324,U20B2049,U21B2018)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.