Abstract
Recent studies have demonstrated that generative models, such as Generative Adversarial Networks (GANs), leave discernible traces in their results. Based on these traces, several forensic methods have achieved remarkable detection accuracy and strong generalization across different generative models. To counter forensic methods and identify potential vulnerabilities in detectors, existing anti-forensics methods primarily focus on embedding adversarial noises into spacial images. In addition, most methods design distinct noise patterns to each image, making it challenging to generate many adversarial samples within a short time. To address these limitations, this paper proposes a novel anti-forensics method in the frequency domain via using image pairs generated with GAN inversion technology. The objective is to design a universally effective approach that avoids introducing noticeable spatial traces. The proposed method introduces a fresh perspective by applying GAN inversion technology to the field of frequency-domain anti-forensics and only requires 100 images, which is effective to handle all the outputs of the target generator and to generate numerous adversarial samples in turn to help enhance the performance of the detector. Our experiment results show a significant reduction of the detection performance. Specially, when two target models detect both generated and edited images based on the StyleGAN, the area under the receiver-operating curve (AUC) decreases by 9.0\(\%\).
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
Abdal, R., Qin, Y., Wonka, P.: Image2stylegan++: how to edit the embedded images? In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8296–8305. IEEE (2020). https://doi.org/10.1109/CVPR42600.2020.00832
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 (CVPRW), pp. 658–659. IEEE (2020). https://doi.org/10.1109/CVPRW50498.2020.00337
Chai, L., Bau, D., Lim, S.-N., Isola, P.: What makes fake images detectable? Understanding properties that generalize. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 103–120. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58574-7_7
Corvi, R., Cozzolino, D., Zingarini, G., Poggi, G., Nagano, K., Verdoliva, L.: On the detection of synthetic images generated by diffusion models. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1–5. IEEE (2023). https://doi.org/10.1109/ICASSP49357.2023.10095167
Cozzolino, D., Thies, J., Rossler, A., Nießner, M., Verdoliva, L.: SpoC: spoofing camera fingerprints. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 990–1000. IEEE (2021). https://doi.org/10.1109/CVPRW53098.2021.00110
Durall, R., Keuper, M., Keuper, J.: Watch your up-convolution: CNN based generative deep neural networks are failing to reproduce spectral distributions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7890–7899. IEEE (2020). https://doi.org/10.1109/CVPR42600.2020.00791
Frank, J., Eisenhofer, T., Schönherr, L., Fischer, A., Kolossa, D., Holz, T.: Leveraging frequency analysis for deep fake image recognition. In: Proceedings of the 37th International Conference on Machine Learning, pp. 3247–3258. ICML 2020, JMLR.org (2020)
Gragnaniello, D., Cozzolino, D., Marra, F., Poggi, G., Verdoliva, L.: Are GAN generated images easy to detect? a critical analysis of the state-of-the-art. In: Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), pp. 1–6. IEEE (2021). https://doi.org/10.1109/ICME51207.2021.9428429
Härkönen, E., Hertzmann, A., Lehtinen, J., Paris, S.: Ganspace: Discovering interpretable GAN controls. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. NIPS 2020, vol. 33, pp. 9841–9850 (2020)
Huang, Y., Juefei-Xu, F., Guo, Q., Liu, Y., Pu, G.: Dodging deepfake detection via implicit spatial-domain notch filtering. IEEE Trans. Circ. Syst. Video Technol. (2023). https://doi.org/10.1109/TCSVT.2023.3325427
Jiang, L., Dai, B., Wu, W., Loy, C.C.: Focal frequency loss for image reconstruction and synthesis. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 13919–13929. IEEE (2021). https://doi.org/10.1109/ICCV48922.2021.01366
Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4401–4410. IEEE (2019). https://doi.org/10.1109/CVPR.2019.00453
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110–8119. IEEE (2020). https://doi.org/10.1109/CVPR42600.2020.00813
Lee, S.H., et al.: Sound-guided semantic image manipulation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3377–3386. IEEE (2022). https://doi.org/10.1109/CVPR52688.2022.00337
Mahmood, K., Mahmood, R., Rathbun, E., van Dijk, M.: Back in black: a comparative evaluation of recent state-of-the-art black-box attacks. IEEE Access 10, 998–1019 (2022). https://doi.org/10.1109/ACCESS.2021.3138338
Marra, F., Gragnaniello, D., Verdoliva, L., Poggi, G.: Do GANs leave artificial fingerprints? In: Proceedings of the IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), pp. 506–511. IEEE, IEEE (2019). https://doi.org/10.1109/MIPR.2019.00103
Nataraj, L., et al.: Detecting GAN generated fake images using co-occurrence matrices. Electronic Imaging 31(5), 532–1–532-7 (2019). https://doi.org/10.2352/ISSN.2470-1173.2019.5.MWSF-532
Neves, J.C., Tolosana, R., Vera-Rodriguez, R., Lopes, V., Proença, H., Fierrez, J.: GANprintr: improved fakes and evaluation of the state of the art in face manipulation detection. IEEE J. Sel. Top. Sig. Process. 14(5), 1038–1048 (2020). https://doi.org/10.1109/JSTSP.2020.3007250
Platt, J., et al.: Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv. Large Margin Classifiers 10(3), 61–74 (1999)
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10674–10685. IEEE (2022). https://doi.org/10.1109/CVPR52688.2022.01042
Shen, Y., Gu, J., Tang, X., Zhou, B.: Interpreting the latent space of GANs for semantic face editing. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9243–9252. IEEE (2020). https://doi.org/10.1109/CVPR42600.2020.00926
Shen, Y., Zhou, B.: Closed-form factorization of latent semantics in GANs. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1532–1540. IEEE (2021). https://doi.org/10.1109/CVPR46437.2021.00158
Tov, O., Alaluf, Y., Nitzan, Y., Patashnik, O., Cohen-Or, D.: Designing an encoder for styleGAN image manipulation. ACM Trans. Graph. 40(4), 1–14 (2021). https://doi.org/10.1145/3450626.3459838
Wang, S.Y., Wang, O., Zhang, R., Owens, A., Efros, A.A.: CNN-generated images are surprisingly easy to spot... for now. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8695–8704. IEEE (2020). https://doi.org/10.1109/CVPR42600.2020.00872
Wei, W., Feng, Z., Min, T., Junjie, C., Hongjun, L.: Survey on anti-forensics techniques of digital image. J. Image Graph. 21(12), 11 (2016). https://doi.org/10.11834/JIG.20161201
Xia, W., Zhang, Y., Yang, Y., Xue, J.H., Zhou, B., Yang, M.H.: Gan inversion: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3121–3138 (2023). https://doi.org/10.1109/TPAMI.2022.3181070
Ye, D., Jie, W., Qi, W., Qing, L.: Analysis of adversarial examples from frequency domain. Inf. Technol. Netw. Secur./Xinxi Jishu yu Wangluo Anquan 41(5) (2022). https://doi.org/10.19358/J.ISSN.2096-5133.2022.05.009
Zhang, R.: Making convolutional networks shift-invariant again. In: Proceedings of the 36th International Conference on Machine Learning. ICML 2019, vol. 97, pp. 7324–7334. PMLR (2019)
Zhang, X., Karaman, S., Chang, S.F.: Detecting and simulating artifacts in GAN fake images. In: Proceedings of the IEEE International Workshop on Information Forensics and Security (WIFS), pp. 1–6. IEEE (2019). https://doi.org/10.1109/WIFS47025.2019.9035107
Acknowledgments
This work was supported by National Key Technology Research and Development Program under 2020AAA0140000.
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
Pu, H., Yi, X., Yang, B., Zhao, X., Liu, C. (2024). Inversion Image Pairs for Anti-forensics in the Frequency Domain. In: Ma, B., Li, J., Li, Q. (eds) Digital Forensics and Watermarking. IWDW 2023. Lecture Notes in Computer Science, vol 14511. Springer, Singapore. https://doi.org/10.1007/978-981-97-2585-4_13
Download citation
DOI: https://doi.org/10.1007/978-981-97-2585-4_13
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2584-7
Online ISBN: 978-981-97-2585-4
eBook Packages: Computer ScienceComputer Science (R0)