CoChat

Preventing DeepFake Attacks on Speaker Authentication by Dynamic Lip Movement Analysis

Open access
Yang, Chen-Zhao, Ma, Jun, Wang, Shilin, Liew, Alan Wee-Chung · 2021 · IEEE Transactions on Information Forensics and Security
Cited by 95

The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.

Abstract

Recent research has demonstrated that lip-based speaker authentication systems can not only achieve good authentication performance but also guarantee liveness. However, with modern DeepFake technology, attackers can produce the talking video of a user without leaving any visually noticeable fake traces. This can seriously compromise traditional face-based or lip-based authentication systems. To defend against sophisticated DeepFake attacks, a new visual speaker authentication scheme based on the deep convolutional neural network (DCNN) is proposed in this paper. The proposed network is composed of two functional parts, namely, the Fundamental Feature Extraction network (FFE-Net) and the Representative lip feature extraction and Classification network (RC-Net). The FFE-Net provides the fundamental information for speaker authentication. As the static lip shape and lip appearance is vulnerable to DeepFake attacks, the dynamic lip movement is emphasized in the FFE-Net. The RC-Net extracts high-level lip features that discriminate against human imposters while capturing the client's talking style. A multi-task learning scheme is designed, and the proposed network is trained end-to-end. Experiments on the GRID and MOBIO datasets have demonstrated that the proposed approach is able to achieve an accurate authentication result against human imposters and is much more robust against DeepFake attacks compared to three state-of-the-art visual speaker authentication algorithms. It is also worth noting that the proposed approach does not require any prior knowledge of the DeepFake spoofing method and thus can be applied to defend against different kinds of DeepFake attacks.

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/tifs.2020.3045937

Cites

27 of 27 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: 43

  1. messer, 1999, XM2VTSDB: The extended M2VTS database, Proc of the first international conference on Audio-and Video-based Biometric Person Authentication, 964
  2. 2020, DeepFaceLab
  3. bitesize, 2019, Deepfakes What are They and Why Would i Make One
  4. brox, 2004, High accuracy optical flow estimation based on a theory for warping, Proc ECCV, 3024, 25
  5. 10.1109/ICCV.2009.5459375 · DOI · Paper page
  6. 10.1121/1.2229005 · DOI · Paper page
  7. 10.1109/ICMEW.2012.116 · DOI · Paper page
  8. luettin, 1998, Evaluation protocol for the XM2FDB database (Lausanne Protocol), Communication 98–05
  9. ioffe, 2015, Batch normalization: Accelerating deep network training by reducing internal covariate shift, Proc 32nd Int Conf Mach Learn (ICML), 448
  10. nair, 2010, Rectified linear units improve restricted Boltzmann machines, Proc 27th Int Conf Mach Learn (ICML), 807
  11. 10.1155/2009/284124 · DOI
  12. 10.1109/CCST.2004.1405380 · doi:10.1109/ccst.2004.1405380
  13. 10.1016/j.ins.2016.09.015 · doi:10.1016/j.ins.2016.09.015
  14. 10.1007/978-3-030-36808-1_18 · DOI
  15. 10.1016/j.patcog.2018.06.005 · DOI
  16. liao, 2008, Video-based person authetication with random passwords, Proc IEEE Int Conf Multimedia Expo, 581
  17. 2020, faceswap-gan
  18. 2020, Faceswap
  19. farnebäck, 2003, Two-frame motion estimation based on polynomial expansion, Proc 13th Scandin Conf Image Anal, 363
  20. agarwal, 2019, Protecting world leaders against deep fakes, Proc IEEE/CVF Conf Comput Vis Pattern Recognit (CVPR) Workshops, 38
  21. 10.2139/ssrn.3419272 · DOI
  22. 10.1109/CVPRW50498.2020.00338 · DOI · Paper page
  23. 10.1109/ICSLP.1996.607030 · doi:10.1109/icslp.1996.607030
  24. 10.1109/TENCON.1997.647280 · doi:10.1109/tencon.1997.647280
  25. 10.1109/ICASSP.2000.859322 · doi:10.1109/icassp.2000.859322
  26. broun, 2002, Automatic speechreading with application to speaker verification, Proc IEEE Int Conf Acoust Speech Signal Process, 685
  27. 10.1109/TIP.2006.877528 · DOI
  28. 10.1016/j.patcog.2012.02.016 · doi:10.1016/j.patcog.2012.02.016
  29. 10.1109/TIFS.2013.2293025 · DOI
  30. 10.1109/34.982900 · DOI · Paper page
  31. 10.1109/TMM.2009.2030637 · DOI · Paper page
  32. 10.1109/TIFS.2011.2175920 · DOI
  33. 10.1109/TIFS.2018.2833033 · DOI
  34. 10.1155/2016/8973828 · doi:10.1155/2016/8973828
  35. 10.1109/ICIE.2010.31 · doi:10.1109/icie.2010.31
  36. 10.1007/s10044-005-0241-x · DOI
  37. 10.1109/TIFS.2018.2801312 · DOI · Paper page
  38. 10.1109/TIFS.2015.2458700 · doi:10.1109/tifs.2015.2458700
  39. 10.1049/iet-bmt.2017.0079 · DOI
  40. 10.1109/TIFS.2018.2876748 · DOI · Paper page
  41. 10.1145/2929464.2929475 · DOI · Paper page
  42. 10.5244/C.29.41 · DOI · Paper page
  43. 10.1109/AINA.2017.53 · DOI · Paper page

Cited by

See all 95

Metadata

Authors
Yang, C.-Z., Ma, J., Wang, S., & Liew, A. W.-C.
Venue
IEEE Transactions on Information Forensics and Security
Published
2021
Volume
16
Pages
1841-1854
ISSN
  • 1556-6013 (ISSN-L)
  • 1556-6021
OpenAlex
W3113824005
Cited by
95
References
27
FWCI
5.51
Type
journal article
Language
en
Open access
green
Funders
National Natural Science Foundation of China (61771310)

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.