Abstract
The quality of image generation and manipulation is reaching impressive levels, making it increasingly difficult for a human to distinguish between what is real and what is fake. However, deep networks can still pick up on the subtle artifacts in these doctored images. We seek to understand what properties of fake images make them detectable and identify what generalizes across different model architectures, datasets, and variations in training. We use a patch-based classifier with limited receptive fields to visualize which regions of fake images are more easily detectable. We further show a technique to exaggerate these detectable properties and demonstrate that, even when the image generator is adversarially finetuned against a fake image classifier, it is still imperfect and leaves detectable artifacts in certain image patches. Code is available at https://github.com/chail/patch-forensics.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Deepfakes.https://github.com/deepfakes/faceswap
Afchar, D., Nozick, V., Yamagishi, J., Echizen, I.: MesoNet: a compact facial video forgery detection network. In: 2018 IEEE International Workshop on Information Forensics and Security (WIFS), pp. 1–7. IEEE (2018)
Bau, D., et al.: Seeing what a GAN cannot generate. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4502–4511 (2019)
Bayar, B., Stamm, M.C.: A deep learning approach to universal image manipulation detection using a new convolutional layer. In: Proceedings of the 4th ACM Workshop on Information Hiding and Multimedia Security, pp. 5–10 (2016)
Carlini, N., Farid, H.: Evading deepfake-image detectors with white-and black-box attacks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 658–659 (2020)
Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251–1258 (2017)
Cozzolino, D., Poggi, G., Verdoliva, L.: Recasting residual-based local descriptors as convolutional neural networks: an application to image forgery detection. In: Proceedings of the 5th ACM Workshop on Information Hiding and Multimedia Security, pp. 159–164 (2017)
Cozzolino, D., Thies, J., Rössler, A., Riess, C., Nießner, M., Verdoliva, L.: ForensicTransfer: weakly-supervised domain adaptation for forgery detection. arXiv preprint arXiv:1812.02510 (2018)
Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., Brendel, W.: ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv preprint arXiv:1811.12231 (2018)
Goetschalckx, L., Andonian, A., Oliva, A., Isola, P.: GANalyze: toward visual definitions of cognitive image properties. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5744–5753 (2019)
Gragnaniello, D., Marra, F., Poggi, G., Verdoliva, L.: Analysis of adversarial attacks against CNN-based image forgery detectors. In: 2018 26th European Signal Processing Conference (EUSIPCO), pp. 967–971. IEEE (2018)
Hays, J., Efros, A.A.: Scene completion using millions of photographs. ACM Trans. Graph. (TOG) 26(3), 4-es (2007)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778 (2016)
Huh, M., Liu, A., Owens, A., Efros, A.A.: Fighting fake news: image splice detection via learned self-consistency. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 106–124. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01252-6_7
Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125–1134 (2017)
Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)
Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4401–4410 (2019)
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. arXiv preprint arXiv:1912.04958 (2019)
Kingma, D.P., Dhariwal, P.: Glow: generative flow with invertible 1x1 convolutions. In: Advances in Neural Information Processing Systems, pp. 10215–10224 (2018)
Li, C., Wand, M.: Precomputed real-time texture synthesis with Markovian generative adversarial networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 702–716. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_43
Li, L., Bao, J., Zhang, T., Yang, H., Chen, D., Wen, F., Guo, B.: Face x-ray for more general face forgery detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5001–5010 (2020)
Li, Y., Lyu, S.: Exposing deepfake videos by detecting face warping artifacts. arXiv preprint arXiv:1811.00656 (2018)
Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of International Conference on Computer Vision (ICCV), December 2015
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Mayer, O., Stamm, M.C.: Exposing fake images with forensic similarity graphs. arXiv preprint arXiv:1912.02861 (2019)
Mo, H., Chen, B., Luo, W.: Fake faces identification via convolutional neural network. In: Proceedings of the 6th ACM Workshop on Information Hiding and Multimedia Security, pp. 43–47 (2018)
Popescu, A.C., Farid, H.: Exposing digital forgeries by detecting duplicated image regions. Dept. Comput. Sci., Dartmouth College, Technical report TR2004-515 pp. 1–11 (2004)
Popescu, A.C., Farid, H.: Exposing digital forgeries by detecting traces of resampling. IEEE Trans. Signal Process. 53(2), 758–767 (2005)
Popescu, A.C., Farid, H.: Exposing digital forgeries in color filter array interpolated images. IEEE Trans. Signal Process. 53(10), 3948–3959 (2005)
Rahmouni, N., Nozick, V., Yamagishi, J., Echizen, I.: Distinguishing computer graphics from natural images using convolution neural networks. In: 2017 IEEE Workshop on Information Forensics and Security (WIFS), pp. 1–6. IEEE (2017)
Richardson, E., Weiss, Y.: On GANs and GMMs. In: Advances in Neural Information Processing Systems, pp. 5847–5858 (2018)
Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., Nießner, M.: Faceforensics++: learning to detect manipulated facial images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1–11 (2019)
Wang, S.Y., Wang, O., Zhang, R., Owens, A., Efros, A.A.: CNN-generated images are surprisingly easy to spot... for now. arXiv preprint arXiv:1912.11035 (2019)
Xuan, X., Peng, B., Wang, W., Dong, J.: On the generalization of GAN image forensics. In: Sun, Z., He, R., Feng, J., Shan, S., Guo, Z. (eds.) CCBR 2019. LNCS, vol. 11818, pp. 134–141. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-31456-9_15
Yu, N., Davis, L.S., Fritz, M.: Attributing fake images to GANs: learning and analyzing GAN fingerprints. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7556–7566 (2019)
Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 586–595 (2018)
Zhang, X., Karaman, S., Chang, S.F.: Detecting and simulating artifacts in GAN fake images. arXiv preprint arXiv:1907.06515 (2019)
Zhou, P., Han, X., Morariu, V.I., Davis, L.S.: Two-stream neural networks for tampered face detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1831–1839. IEEE (2017)
Acknowledgements
We thank Antonio Torralba, Jonas Wulff, Jacob Huh, Tongzhou Wang, Harry Yang, and Richard Zhang for helpful discussions. This work was supported by a National Science Foundation Graduate Research Fellowship under Grant No. 1122374 to L.C. and DARPA XAI FA8750-18-C000-4 to D.B.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Chai, L., Bau, D., Lim, SN., Isola, P. (2020). What Makes Fake Images Detectable? Understanding Properties that Generalize. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12371. Springer, Cham. https://doi.org/10.1007/978-3-030-58574-7_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-58574-7_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58573-0
Online ISBN: 978-3-030-58574-7
eBook Packages: Computer ScienceComputer Science (R0)