CoChat

A Novel Counterfeit Feature Extraction Technique for Exposing Face-Swap Images Based on Deep Learning and Error Level Analysis

Open access
Zhang, Weiguo, Zhao, Chenggang, Li, Yuxing · 2020 · Entropy
Cited by 60

The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.

Abstract

The quality and efficiency of generating face-swap images have been markedly strengthened by deep learning. For instance, the face-swap manipulations by DeepFake are so real that it is tricky to distinguish authenticity through automatic or manual detection. To augment the efficiency of distinguishing face-swap images generated by DeepFake from real facial ones, a novel counterfeit feature extraction technique was developed based on deep learning and error level analysis (ELA). It is related to entropy and information theory such as cross-entropy loss function in the final softmax layer. The DeepFake algorithm is only able to generate limited resolutions. Therefore, this algorithm results in two different image compression ratios between the fake face area as the foreground and the original area as the background, which would leave distinctive counterfeit traces. Through the ELA method, we can detect whether there are different image compression ratios. Convolution neural network (CNN), one of the representative technologies of deep learning, can extract the counterfeit feature and detect whether images are fake. Experiments show that the training efficiency of the CNN model can be significantly improved by the ELA method. In addition, the proposed technique can accurately extract the counterfeit feature, and therefore achieves outperformance in simplicity and efficiency compared with direct detection methods. Specifically, without loss of accuracy, the amount of computation can be significantly reduced (where the required floating-point computing power is reduced by more than 90%).

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 · 10.3390/e22020249

Cites

9 of 9 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

Show all 9 references

Research works printed but not linked: 17

  1. Liu, M.Y., Breuel, T., and Kautz, J. (2017, January 4–9). Unsupervised Image-to-Image Translation Networks. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
  2. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial nets. NIPS’14, Proceedings of the 27th International Conference on Neural Information Processing Systems, MIT Press.
  3. Schetinger, 2017, Humans are easily fooled by digital images, Comput. Graph., 68, 142, 10.1016/j.cag.2017.08.010 · DOI · Paper page
  4. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
  5. Li, H., Li, B., Tan, S., and Huang, J. (2018). Detection of deep network generated images using disparities in color components. arXiv.
  6. Cpatel, 2015, An Improvement of Forgery Video Detection Technique using Error Level Analysis, Int. J. Comput. Appl., 111, 26
  7. Jeronymo, 2017, Image Forgery Detection by Semi-Automatic Wavelet Soft-Thresholding with Error Level Analysis, Expert Syst. Appl., 85, 348, 10.1016/j.eswa.2017.05.044 · DOI
  8. Sudiatmika, 2019, Image forgery detection using error level analysis and deep learning, Telkomnika, 17, 653, 10.12928/telkomnika.v17i2.8976 · doi:10.12928/telkomnika.v17i2.8976
  9. Krawetz, N. (August, January 31). A picture’s worth digital image analysis and forensics. Proceedings of the 2007 Black Hat Briefings, Caesars Palace, LV, USA.
  10. Garcia, 2004, Convolutional face finder: A neural architecture for fast and robust face detection, IEEE Trans. Pattern Anal. Mach. Intell., 26, 1408, 10.1109/TPAMI.2004.97 · DOI · Paper page
  11. Lawrence, 1997, Face recognition: A convolutional neural-network approach, IEEE Trans. Neural Netw., 8, 98, 10.1109/72.554195 · DOI · Paper page
  12. Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., and Fei-Fei, L. (2014, January 23–28). Large-Scale Video Classification with Convolutional Neural Networks. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA. · DOI · Paper page
  13. Dong, 2016, Image Super-Resolution Using Deep Convolutional Networks, IEEE Trans. Pattern Anal. Mach. Intell., 38, 295, 10.1109/TPAMI.2015.2439281 · DOI · Paper page
  14. Dong, J., Wang, W., and Tan, T. (2013). Casia image tampering detection evaluation database. Signal and Information Processing (ChinaSIP), Proceedings of the 2013 IEEE China Summit & International Conference, Beijing, China, 6–10 July 2013, IEEE. · DOI · Paper page
  15. Riess, 2013, Exposing digital image forgeries by illumination color classification, IEEE Trans. Inf. Forensics Secur., 8, 1182, 10.1109/TIFS.2013.2265677 · DOI · Paper page
  16. Koshy, R., and Mahmood, A. (2019). Optimizing Deep CNN Architectures for Face Liveness Detection. Entropy, 21. · DOI
  17. Schetinger, 2017, Image forgery detection confronts image composition, Comput. Graph., 68, 152, 10.1016/j.cag.2017.08.014 · DOI

Cited by

Metadata

Authors
Zhang, W., Zhao, C., & Li, Y.
Venue
Entropy
Publisher
MDPI AG
Published
2020-02-21
Volume
22
Issue
2
Pages
249
ISSN
1099-4300 (ISSN-L)
OpenAlex
W3008227768
Cited by
60
References
9
FWCI
2.92
Type
journal article
Language
en
Open access
gold
Funders
National Natural Science Foundation of China (11574250, 61603296)

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.