Abstract
As Generative Adversarial Networks continue to evolve, deepfake images have become notably more realistic, escalating societal, economic, and political threats. Consequently, deepfake detection has emerged as a crucial research area to deal with these rising threats. Additionally, deepfake disruption, a method that introduces proactive perturbations to genuine images to thwart deepfake generation, has arisen as a prospective defense mechanism. While adopting these two strategies simultaneously seems beneficial in countering deepfakes, this paper first highlights a concern related to their co-existence: genuine images gathered from the Internet, already imbued with disrupting perturbations, can lead to data poisoning in the training datasets of deepfake detection models, thereby severely affecting detection accuracy. This problem, despite its practical implications, has not been adequately addressed in previous deepfake detection studies. This paper proposes a novel training framework to address this problem. Our approach purifies disruptive perturbations during model training using a reverse process of the denoising diffusion probabilistic model. This purification process, faster than the leading method called DiffPure, enables successful deepfake image generation for training and significantly curtails accuracy loss in poisoned datasets. Demonstrating superior performance across detection models, our framework anticipates broad applicability. Our implementation is available at https://github.com/seclab-yonsei/Anti-disrupt.
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
References
Asnani, V., Yin, X., Hassner, T., Liu, S., Liu, X.: Proactive image manipulation detection. In: Proceedings of the CVPR, pp. 15386–15395 (2022)
Choi, Y., Choi, M., Kim, M., Ha, J.W., Kim, S., Choo, J.: StarGAN: unified generative adversarial networks for multi-domain image-to-image translation. In: Proceedings of the CVPR, pp. 8789–8797 (2018)
Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the CVPR (2017)
Ciftci, U.A., Demir, I., Yin, L.: FakeCatcher: detection of synthetic portrait videos using biological signals. IEEE Trans. Pattern Anal. Mach. Intell. (2020)
Goodfellow, I.J., et al.: Generative adversarial networks (2014)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the CVPR, pp. 770–778 (2016)
Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840–6851 (2020)
Hsu, G.S., Tsai, C.H., Wu, H.Y.: Dual-generator face reenactment. In: Proceedings of the CVPR, pp. 642–650 (2022)
Hu, S., Li, Y., Lyu, S.: Exposing GAN-generated faces using inconsistent corneal specular highlights. In: Proceedings of the ICASSP, pp. 2500–2504. IEEE (2021)
Huang, Q., Zhang, J., Zhou, W., Zhang, W., Yu, N.: Initiative defense against facial manipulation. In: Proceedings of the AAAI, vol. 35, pp. 1619–1627 (2021)
Hulzebosch, N., Ibrahimi, S., Worring, M.: Detecting CNN-generated facial images in real-world scenarios. In: Proceedings of the CVPR Workshops (2020)
Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the CVPR, pp. 4401–4410 (2019)
Lee, K., Kim, J., Chong, S., Shin, J.: Making stochastic neural networks from deterministic ones (2017)
Li, Y., Lyu, S.: Exposing deepfake videos by detecting face warping artifacts. arXiv preprint arXiv:1811.00656 (2018)
Li, Y., Yang, X., Sun, P., Qi, H., Lyu, S.: Celeb-DF: a large-scale challenging dataset for deepfake forensics. In: Proceedings of the CVPR, pp. 3207–3216 (2020)
Liu, B., Yang, F., Bi, X., Xiao, B., Li, W., Gao, X.: Detecting generated images by real images. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13674, pp. 95–110. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19781-9_6
Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings OF the ICCV (2015)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: Proceedings of the ICLR (2018)
Meng, D., Chen, H.: Magnet: a two-pronged defense against adversarial examples. In: Proceedings of the CCS, pp. 135–147 (2017)
Nie, W., Guo, B., Huang, Y., Xiao, C., Vahdat, A., Anandkumar, A.: Diffusion models for adversarial purification. In: Proceedings of the ICML, pp. 16805–16827. PMLR (2022)
Nirkin, Y., Keller, Y., Hassner, T.: FSGAN: subject agnostic face swapping and reenactment. In: Proceedings of the ICCV, pp. 7184–7193 (2019)
Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., Nießner, M.: Faceforensics++: learning to detect manipulated facial images. In: Proceedings of the ICCV, pp. 1–11 (2019)
Ruiz, N., Bargal, S.A., Sclaroff, S.: Disrupting deepfakes: adversarial attacks against conditional image translation networks and facial manipulation systems. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12538, pp. 236–251. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-66823-5_14
Wang, R., Huang, Z., Chen, Z., Liu, L., Chen, J., Wang, L.: Anti-forgery: towards a stealthy and robust deepfake disruption attack via adversarial perceptual-aware perturbations. arXiv preprint arXiv:2206.00477 (2022)
Wang, X., Huang, J., Ma, S., Nepal, S., Xu, C.: Deepfake disrupter: the detector of deepfake is my friend. In: Proceedings of the CVPR, pp. 14920–14929 (2022)
Xia, W., Yang, Y., Xue, J.H., Wu, B.: TediGAN: text-guided diverse face image generation and manipulation. In: Proceedings of the CVPR, pp. 2256–2265 (2021)
Yang, X., Li, Y., Lyu, S.: Exposing deep fakes using inconsistent head poses. In: Proceedings of the ICASSP, pp. 8261–8265. IEEE (2019)
Yeh, C.Y., Chen, H.W., Tsai, S.L., Wang, S.D.: Disrupting image-translation-based deepfake algorithms with adversarial attacks. In: Proceedings of the WACV Workshops, pp. 53–62 (2020)
Zhang, X., Karaman, S., Chang, S.F.: Detecting and simulating artifacts in GAN fake images. In: Proceedings of the WIFS, pp. 1–6. IEEE (2019)
Zhu, Y., Li, Q., Wang, J., Xu, C.Z., Sun, Z.: One shot face swapping on megapixels. In: Proceedings of the CVPR, pp. 4834–4844 (2021)
Acknowledgments
This work was supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea Government (MSIT) (No.RS-2023-00230337) and by the ITRC (Information Technology Research Center) support program (IITP-2023-2020-0-01602).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Park, J., Ahn, H.E., Park, L.H., Kwon, T. (2024). Robust Training for Deepfake Detection Models Against Disruption-Induced Data Poisoning. In: Kim, H., Youn, J. (eds) Information Security Applications. WISA 2023. Lecture Notes in Computer Science, vol 14402. Springer, Singapore. https://doi.org/10.1007/978-981-99-8024-6_14
Download citation
DOI: https://doi.org/10.1007/978-981-99-8024-6_14
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8023-9
Online ISBN: 978-981-99-8024-6
eBook Packages: Computer ScienceComputer Science (R0)