GAN模型生成图像检测方法综述

doi:10.3778/j.issn.1002-8331.2405-0346

摘要/Abstract

摘要： 生成对抗网络（generative adversarial network，GAN）作为生成高质量图像的强大工具，近年来在图像合成领域得到了广泛应用。然而，随着GAN技术的快速发展，引发了图像伪造和欺诈的严重担忧，特别是在新闻报道、身份认证以及司法取证等关键领域。这些伪造图像不仅难以辨别，还可能被用于传播虚假信息、实施诈骗，甚至在法律案件中造成难以弥补的损害。为应对这一挑战，研究者们提出了多种检测GAN生成图像的方法，主要可以分为基于特征识别的方法和基于数据驱动的方法。对于当前主要的GAN图像检测方法进行了系统梳理，并通过重训练实验验证了它们在不同数据集上的检测准确率。对未来GAN图像检测领域的发展趋势进行了展望，提出了潜在的研究方向，以推动该领域的进一步创新和发展。

关键词: 生成对抗网络（GAN）, 深度学习, 伪造检测

Abstract: As a powerful tool for generating high-quality images, generative adversarial network (GAN) has been widely used in the field of image synthesis in recent years. However, with the rapid development of GAN technology, it also raises serious concerns about image forgery and fraud, especially in key areas such as news reporting, identity authentication and judicial forensics. These fake images not only are difficult to identify, but also may be used to spread false information, commit fraud, or even cause irreparable damage in legal cases. To cope with this challenge, researchers have proposed a variety of methods for detecting GAN-generated images, which can be mainly divided into feature-based methods and data-driven methods. This paper systematically sorts out the current main GAN image detection methods, and verifies their detection accuracy on different datasets through re-training experiments. Finally, the development trend of GAN image detection in the future is prospected, and potential research directions are proposed, in order to promote further innovation and development in this field.

Key words: generative adversarial network (GAN), deep learning, forgery detection

谢天圻, 吴媛媛, 敬超, 孙伟恒. GAN模型生成图像检测方法综述[J]. 计算机工程与应用, 2024, 60(22): 74-86.

XIE Tianqi, WU Yuanyuan, JING Chao, SUN Weiheng. Survey of Image Detection Methods Generated by GAN Models[J]. Computer Engineering and Applications, 2024, 60(22): 74-86.

参考文献

[1] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Advances in Neural Information Processing Systems 27, 2014.
[2] MIRZA M, OSINDERO S. Conditional generative adversarial nets[J]. arXiv:1411.1784, 2014.
[3] RADFORD A, METZ L, CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks[J]. arXiv:1511.06434, 2015.
[4] BROCK A, DONAHUE J, SIMONYAN K. Large scale GAN training for high fidelity natural image synthesis[J]. arXiv:1809.11096, 2018.
[5] KARRAS T, LAINE S, AILA T. A style-based generator architecture for generative adversarial networks[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 4401-4410.
[6] TAO M, BAO B K, TANG H, et al. GALIP: generative adversarial clips for text-to-image synthesis[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 14214-14223.
[7] RADFORD A, KIM J W, HALLACY C, et al. Learning transferable visual models from natural language supervision[C]//Proceedings of the 38th International Conference on Machine Learning, 2021: 8748-8763.
[8] KANG M, ZHU J Y, ZHANG R, et al. Scaling up GANs for text-to-image synthesis[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 10124-10134.
[9] SCHUHMANN C, BEAUMONT R, VENCU R, et al. LAION-5B: an open large-scale dataset for training next generation image-text models[C]//Advances in Neural Information Processing Systems 35, 2022: 25278-25294.
[10] WANG X, LI Y, ZHANG H, et al. Towards real-world blind face restoration with generative facial prior[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 9168-9178.
[11] LEDIG C, THEIS L, HUSZáR F, et al. Photo-realistic single image super-resolution using a generative adversarial network[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017: 4681-4690.
[12] COZZOLINO D, GRAGNANIELLO D, VERDOLIVA L. Image forgery detection through residual-based local descriptors and block-matching[C]//Proceedings of the 2014 IEEE International Conference on Image Processing, 2014: 5297-5301.
[13] NATARAJ L, MOHAMMED T M, CHANDRASEKARAN S, et al. Detecting GAN generated fake images using co-occurrence matrices[J]. arXiv:1903.06836, 2019.
[14] LI H, LI B, TAN S, et al. Identification of deep network generated images using disparities in color components[J]. Signal Processing, 2020, 174: 107616.
[15] MATERN F, RIESS C, STAMMINGER M. Exploiting visual artifacts to expose deepfakes and face manipulations[C]//Proceedings of the 2019 IEEE Winter Applications of Computer Vision Workshops, 2019: 83-92.
[16] MCCLOSKEY S, ALBRIGHT M. Detecting GAN-generated imagery using saturation cues[C]//Proceedings of the 2019 IEEE International Conference on Image Processing, 2019: 4584-4588.
[17] ZHANG X, KARAMAN S, CHANG S F. Detecting and simulating artifacts in GAN fake images[C]//Proceedings of the 2019 IEEE International Workshop on Information Forensics and Security, 2019: 1-6.
[18] KINGMA D P, DHARIWAL P. Glow: generative flow with invertible 1×1 convolutions[C]//Advances in Neural Information Processing Systems 31, 2018.
[19] BI X, LIU B, YANG F, et al. Detecting generated images by real images only[J]. arXiv:2311.00962, 2023.
[20] KARRAS T, LAINE S, AITTALA M, et al. Analyzing and improving the image quality of StyleGAN[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 8110-8119.
[21] ZAMIR S W, ARORA A, KHAN S, et al. CycleISP: real image restoration via improved data synthesis[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 2696-2705.
[22] FRANK J, EISENHOFER T, SCH?NHERR L, et al. Leveraging frequency analysis for deep fake image recognition[C]//Proceedings of the 37th International Conference on Machine Learning, 2020: 3247-3258.
[23] CHAI L, BAU D, LIM S N, et al. What makes fake images detectable? Understanding properties that generalize[C]//Proceedings of the 16th European Conference on Computer Vision, Glasgow, Aug 23-28, 2020. Cham: Springer, 2020: 103-120.
[24] JU Y, JIA S, KE L, et al. Fusing global and local features for generalized ai-synthesized image detection[C]//Proceedings of the 2022 IEEE International Conference on Image Processing, 2022: 3465-3469.
[25] ZHONG N, XU Y, QIAN Z, et al. Rich and poor texture contrast: a simple yet effective approach for ai-generated image detection[J]. arXiv:2311.12397, 2023.
[26] CHIERCHIA G, POGGI G, SANSONE C, et al. A Bayesian-MRF approach for PRNU-based image forgery detection[J]. IEEE Transactions on Information Forensics and Security, 2014, 9(4): 554-567.
[27] SCHERHAG U, DEBIASI L, RATHGEB C, et al. Detection of face morphing attacks based on PRNU analysis[J]. IEEE Transactions on Biometrics, Behavior, and Identity Science, 2019, 1(4): 302-317.
[28] FRIDRICH J, KODOVSKY J. Rich models for steganalysis of digital images[J]. IEEE Transactions on information Forensics and Security, 2012, 7(3): 868-882.
[29] TAN C, ZHAO Y, WEI S, et al. Learning on gradients: generalized artifacts representation for GAN-generated images detection[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 12105-12114.
[30] YU N, DAVIS L S, FRITZ M. Attributing fake images to GANs: learning and analyzing GAN fingerprints[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019: 7556-7566.
[31] MARRA F, SALTORI C, BOATO G, et al. Incremental learning for the detection and classification of GAN-generated images[C]//Proceedings of the 2019 IEEE International Workshop on Information Forensics and Security, 2019: 1-6.
[32] JAVED K, SHAFAIT F. Revisiting distillation and incremental classifier learning[C]//Proceedings of the 14th Asian Conference on Computer Vision, Perth, Dec 2-6, 2018. Cham: Springer, 2018.
[33] LOPEZ-PAZ D, RANZATO M. Gradient episodic memory for continual learning[C]//Advances in Neural Information Processing Systems 30, 2017: 6467-6476.
[34] REBUFFI S A, KOLESNIKOV A, SPERL G, et al. ICARL: incremental classifier and representation learning[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2001-2010.
[35] WANG S Y, WANG O, ZHANG R, et al. CNN-generated images are surprisingly easy to spot for now[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 8695-8704.
[36] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.
[37] RICKER J, DAMM S, HOLZ T, et al. Towards the detection of diffusion model deepfakes[J]. arXiv:2210.14571, 2022.
[38] GRAGNANIELLO D, COZZOLINO D, MARRA F, et al. Are GAN generated images easy to detect? A critical analysis of the state-of-the-art[C]//Proceedings of the 2021 IEEE International Conference on Multimedia and Expo, 2021: 1-6.
[39] 乔通, 陈彧星, 谢世闯, 等. 多色彩通道特征融合的 GAN 合成图像检测方法[J]. 电子学报, 2024, 52(3): 924-936.
QIAO T, CHEN Y X, XIE S C, et al. GAN synthetic image detection using fused features in the multi-color channels[J]. Acta Electronica Sinica, 2024, 52(3): 924-936.
[40] KARRAS T, AILA T, LAINE S, et al. Progressive growing of GANs for improved quality, stability, and variation[J]. arXiv:1710.10196, 2017.
[41] ZHU J Y, PARK T, ISOLA P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision, 2017: 2223-2232.
[42] CHOI Y, CHOI M, KIM M, et al. StarGAN: unified generative adversarial networks for multi-domain image-to-image translation[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018: 8789-8797.
[43] PARK T, LIU M Y, WANG T C, et al. Semantic image synthesis with spatially-adaptive normalization[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 2337-2346.
[44] WEST J, BERGSTROM C. Calling bullshit: the art of skepticism in a data-driven world[M]. New York: Random House, 2020.
[45] DHARIWAL P, NICHOL A. Diffusion models beat GANs on image synthesis[C]//Advances in Neural Information Processing Systems 34, 2021: 8780-8794.
[46] NICHOL A, DHARIWAL P, RAMESH A, et al. GLIDE: towards photorealistic image generation and editing with text-guided diffusion models[J]. arXiv:2112.10741, 2021.
[47] HOLZ D. Midjourney[EB/OL]. [2024-05-13]. https://www.midjourney.com/home/.
[48] ROMBACH R, BLATTMANN A, LORENZ D, et al. High-resolution image synthesis with latent diffusion models[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 10684-10695.
[49] GU S, CHEN D, BAO J, et al. Vector quantized diffusion model for text-to-image synthesis[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 10696-10706.
[50] WUKONG. MindSpore[EB/OL]. [2024-05-13]. https://xihe.mindspore.cn/modelzoo/wukong.
[51] RAMESH A, DHARIWAL P, NICHOL A, et al. Hierarchical text-conditional image generation with CLIP latents[J]. arXiv:2204.06125, 2022.