面向GAN生成图像的被动取证及反取证技术综述

何沛松; 李伟创; 张婧媛; 王宏霞; 蒋兴浩

doi:10.11834/jig.210430

综述 | 浏览量 : 0 下载量: 2851 CSCD: 0

PDF
导出
分享
收藏
专辑

面向GAN生成图像的被动取证及反取证技术综述
Overview of passive forensics and anti-forensics techniques for GAN-generated image
2022年27卷第1期页码：88-110
收稿：2021-06-28，

修回：2021-9-16，

录用：2021-9-23，

纸质出版：2022-01-16
DOI： 10.11834/jig.210430
稿件说明：

移动端阅览

何沛松, 李伟创, 张婧媛, 王宏霞, 蒋兴浩. 面向GAN生成图像的被动取证及反取证技术综述[J]. 中国图象图形学报, 2022,27(1):88-110. DOI： 10.11834/jig.210430.

Peisong He, Weichuang Li, Jingyuan Zhang, Hongxia Wang, Xinghao Jiang. Overview of passive forensics and anti-forensics techniques for GAN-generated image[J]. Journal of Image and Graphics, 2022, 27(1): 88-110. DOI： 10.11834/jig.210430.

摘要

生成对抗网络(generative adversarial network，GAN)快速发展，并在图像生成和图像编辑技术等多个方面取得成功应用。然而，若将上述技术用于伪造身份或制作虚假新闻，则会造成严重的安全隐患。多媒体取证领域的研究者面向GAN生成图像已提出了多种被动取证与反取证方法，但现阶段缺乏相关系统性综述。针对上述问题，本文首先阐述本领域的研究背景和研究意义，然后分析自然图像采集与GAN图像生成过程的区别。根据上述理论基础，详细介绍了现有GAN生成图像的被动取证技术，包括：GAN生成图像检测算法，GAN模型溯源算法和其他相关取证问题。此外，针对不同应用场景介绍基于GAN的反取证技术。最后，通过实验分析当前GAN生成图像被动取证技术所面临的挑战。本文根据对现有技术从理论和实验两方面的分析得到以下结论：现阶段，GAN生成图像的被动取证技术已在空间域和频率域形成了不同技术路线，较好地解决了简单场景下的相关取证问题。针对常见取证痕迹，基于GAN的反取证技术已能够进行有效隐藏。然而，该领域研究仍存在诸多局限：1)取证与反取证技术的可解释性不足；2)取证技术鲁棒性和泛化性较弱；3)反取证技术缺乏多特征域协同的抗分析能力等。上述问题和挑战还需要研究人员继续深入探索。

Abstract

Generative adversarial network (GAN) has developed multimedia techniques like image generation and image editing. However

the issues of abusing GAN to generate fake identities and fake news can cause severe security risks and pose a great threat to the integrity and authenticity of digital images. Researchers in the field of multimedia forensics have proposed a variety of passive forensics and anti-forensics techniques about GAN-generated images

which has achieved the phased research results. In this article

the latest passive forensics and anti-forensics techniques for GAN-generated images are reviewed systematically. First

the research background and research significance about forensics and anti-forensics techniques of GAN-generated images have been illustrated

which can provide novel theories to protect the integrity and authenticity of digital image against the recent deep-learning based image generation/editing techniques and analyze the reliability of current forensic algorithms. The characteristics of several representative unconditional GANs and conditional GANs are illustrated on the aspect of network structure and training strategy for recent GAN-based image generation/editing techniques

where the visual defects caused by early GAN models have been continuously eliminated. Next

the differences between natural image acquisition and GAN image generation are analyzed

including the related signal processing operations. The abnormal traces of GAN images are explained in terms of color components

texture characteristics and global content. Based on the above theoretical foundation

this article introduces current passive forensics techniques of GAN-generated images in detail

including: GAN-generated image detection algorithm

GAN model identification algorithm and other related forensics issues. According to the types of forensic clues

GAN-generated image detection algorithms can be divided into two categories based on spatial information and frequency domain information respectively. The methodologies of feature extraction and classification about forensics traces are introduced

including hand-crafted feature based and convolutional neural network (CNN) based methods. More specifically

this article emphasizes the development process of CNN based detection algorithms

including preprocessing based on prior knowledge of forensics traces

advanced network structure and other training strategies. According to the experimental results

existing methods achieved promising detection performance in simple forensic scenarios. However

when testing samples suffer from post-processing operations or are generated by unseen GAN models

the detection performance will become dramatically worse. Then

GAN model identification algorithms of GAN-generated images are demonstrated

which can be split into two categories based on spatial information and frequency domain information. The characteristics of other related forensics issues are presented as well

i.e.

DeepFake detection

where GAN-based image generation can be regarded as a part of the deep-learning based video forgery pipeline. On the other hand

this article has introduced anti-forensics techniques based on GAN

which includes white-box anti-forensics (attack) methods and black-box anti-forensics (attack) methods according to information required for the attack. Furthermore

existing methods mainly focus on two types of anti-forensics scenarios

including source identification and detection of image editing. Finally

several representative algorithms based on spatial information and frequency domain information are selected for the performance comparison. The open access datasets of GAN-generated images and pristine images are used to construct the training and testing samples. The challenging issues about GAN-based passive forensics are investigated

including robustness against post-processing operations and generalization capability of unknown GAN models. The influence of different preprocessing operations for input images

including resizing and crop

is also investigated. Moreover

the potential confrontation situations in practical applications are also considered

where GAN-generated image detection algorithms are applied to identify anti-forensic pictures based on GAN. Experimental results show that current passive forensics methods are invalid to expose unseen anti-forensic attacks. At present

the passive forensics techniques of GAN-generated images have constructed various technical routes in both the spatial domain and the frequency domain

which are capable to deal with the issues of GAN-generated image detection and GAN model identification in simple scenes. Besides

anti-forensics techniques based on GAN can effectively hide common forensics traces. However

by analyzing the related research works and conducting experiments

we think that the research in this field is still in an initial stage

and there are still many unsolved issues. 1) Insufficient interpretability of forensics and anti-forensics techniques. It is hard to analyze which kind of information (local or global; texture or color) plays a more important role in identifying GAN-generated images while the security of current GAN-based anti-forensics techniques lacks theoretical support; 2) Weak robustness and generalization of forensics techniques. It is valuable to explore other detection frameworks further

such as anomaly detection

which may be more efficient to deal with the continuously updated GAN models and unknown post-processing operations in practical applications; 3) The issue of designing the network structure

loss function and training strategy of anti-forensics techniques to hide newly introduced traces should be explored more carefully due to the lack of anti-forensics capability for multiple feature domains.

关键词

Keywords

references

Agarwal S, Farid H, Gu Y M,He M M, Nagano K and Li H. 2019. Protecting world leaders against deep fakes//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. Long Beach, USA: IEEE: 38-45

Agarwal S, Girdhar N and Raghav H. 2021. A novel neural model based framework for detection of GAN generated fake images//Proceedings of the 11th International Conference on Cloud Computing, Data Science and Engineering. Noida, India: IEEE: 46-51 [ DOI: 10.1109/Confluence51648.2021.9377150 http://dx.doi.org/10.1109/Confluence51648.2021.9377150 ]

Arjovsky M, Chintala S and Bottou L. 2017. Wasserstein generative adversarial networks//Proceedings of the 34th International Conference on Machine Learning. Sydney, Australia: JMLR. org: 214-223

Barni M, Bondi L, Bonettini N, Bestagini P, Costanzo A, Maggini M, Tondi B and Tubaro S. 2017. Aligned and non-aligned double JPEG detection using convolutional neural networks. Journal of Visual Communication and Image Representation, 49: 153-163 [DOI: 10.1016/j.jvcir.2017.09.003]

Barni M, Kallas K, Nowroozi E and Tondi B. 2020. CNN detection of GAN-generated face images based on cross-band co-occurrences analysis//Proceedings of 2020 IEEE International Workshop on Information Forensics and Security. New York, USA: IEEE: 1-6 [ DOI: 10.1109/WIFS49906.2020.9360905 http://dx.doi.org/10.1109/WIFS49906.2020.9360905 ]

Bonettini N, Bestagini P, Milani S and Tubaro S. 2021. On the use of benford's law to detect GAN-generated images//Proceedings of the 25th International Conference on Pattern Recognition (ICPR). Milan, Italy: IEEE: 5495-5502 [ DOI: 10.1109/ICPR48806.2021.9412944 http://dx.doi.org/10.1109/ICPR48806.2021.9412944 ]

Brock A, Donahue J and Simonyan K. 2019. Large scale GAN training for high fidelity natural image synthesis//Proceedings of 2019 International Conference on Learning Representations (ICLR). New Orleans, Louisiana, USA

Chen C, Zhao X W and Stamm M C. 2018. Mislgan: an anti-forensic camera model falsification framework using a generative adversarial network//Proceedings of the 25th IEEE International Conference on Image Processing (ICIP). Athens, Greece: IEEE: 535-539 [ DOI: 10.1109/ICIP.2018.8451503 http://dx.doi.org/10.1109/ICIP.2018.8451503 ]

Chen C, Zhao X W and Stamm M C. 2019. Generative adversarial attacks against deep-learning-based camera model identification. IEEE Transactions on Information Forensics and Security: #8854834 [DOI: 10.1109/TIFS.2019.2945198]

Choi Y, Choi M, Kim M, Ha J W, Kim S and Choo J. 2018. StarGAN: unified generative adversarial networks for multi-domain image-to-image translation//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE: 8789-8797 [ DOI: 10.1109/CVPR.2018.00916 http://dx.doi.org/10.1109/CVPR.2018.00916 ]

Choi Y, Uh Y, Yoo J and Ha J W. 2020. StarGAN v2: diverse image synthesis for multiple domains//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, USA: IEEE: 8185-8194 [ DOI: 10.1109/CVPR42600.2020.00821 http://dx.doi.org/10.1109/CVPR42600.2020.00821 ]

Creswell A, White T, Dumoulin V, Arulkumaran K, Sengupta B and Bharath A A. 2018. Generative adversarial networks: an overview. IEEE Signal Processing Magazine, 35(1): 53-65 [DOI: 10.1109/MSP.2017.2765202]

Cui Q, Meng R H, Zhou Z L, Sun X M and Zhu K W. 2019. An anti-forensic scheme on computer graphic images and natural images using generative adversarial networks. Mathematical Biosciences and Engineering, 16(5): 4923-4935 [DOI: 10.3934/mbe.2019248]

dos Santos Tanaka F H K and Aranha C. 2019. Data augmentation using GANs[EB/OL]. [2021-05-28] . https://arxiv.org/pdf/1904.09135v1.pdf https://arxiv.org/pdf/1904.09135v1.pdf

Durall R, Keuper M and Keuper J. 2020. Watch your up-convolution: CNN based generative deep neural networks are failing to reproduce spectral distributions//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE: 7887-7896 [ DOI: 10.1109/CVPR42600.2020.00791 http://dx.doi.org/10.1109/CVPR42600.2020.00791 ]

Frank J, Eisenhofer T, Schönherr L, Fischer A, Kolossa D and Holz T. 2020. Leveraging frequency analysis for deep fake image recognition//Proceedings of the 37th International Conference on Machine Learning. Vienna, Austria: [s. n.]: 3247-3258

Fridrich J and Kodovsky J. 2012. Rich models for steganalysis of digital images. IEEE Transactions on Information Forensics and Security, 7(3): 868-882 [DOI: 10.1109/TIFS.2012.2190402]

Fu Y, Sun T F, Jiang X H, Xu K and He P S. 2019. Robust GAN-face detection based on dual-channel CNN network//Proceedings of the 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI). Suzhou, China: IEEE: 1-5 [ DOI: 10.1109/CISP-BMEI48845.2019.8965991 http://dx.doi.org/10.1109/CISP-BMEI48845.2019.8965991 ]

Goebel M, Nataraj L, Nanjundaswamy T, Mohammed T M, Chandrasekaran S and Manjunath B S. 2021. Detection, attribution and localization of GAN generated images. Electronic Imaging, 2021(4): 276-1-276-11 [DOI: 10.2352/ISSN.2470-1173.2021.4.MWSF-276]

Goodfellow I J, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A and Bengio Y. 2014. Generative adversarial nets//Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal, Canada: MIT Press: 2672-2680

Guarnera L, Giudice O and Battiato S. 2020. DeepFake detection by analyzing convolutional traces//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Seattle, USA: IEEE: 2841-2850 [ DOI: 10.1109/CVPRW50498.2020.00341 http://dx.doi.org/10.1109/CVPRW50498.2020.00341 ]

Gui J, Sun Z N, Wen Y G, Tao D C and Ye J P. 2020. A review on generative adversarial networks: algorithms, theory, and applications[EB/OL]. [2020-01-20] . https://arxiv.org/pdf/2001.06937.pdf https://arxiv.org/pdf/2001.06937.pdf

Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V and Courville A. 2017. Improved training of wasserstein GANs//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, USA: Curran Associates Inc. : 5769-5779

Gunturk B K, Altunbasak Y and Mersereau R M. 2002. Color plane interpolation using alternating projections. IEEE Transactions on Image Processing, 11(9): 997-1013 [DOI: 10.1109/TIP.2002.801121]

Guo Z Q, Yang G B, Chen J Y and Sun X M. 2021. Fake face detection via adaptive manipulation traces extraction network. Computer Vision and Image Understanding, 204: #103170 [DOI: 10.1016/j.cviu.2021.103170]

He K M, Zhang X Y, Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of 2016 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE: 1063-6919 [ DOI: 10.1109/CVPR.2016.90 http://dx.doi.org/10.1109/CVPR.2016.90 ]

Hulzebosch N, Ibrahimi S and Worring M. 2020. Detecting CNN-generated facial images in real-world scenarios//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Seattle, USA: IEEE: 2729-2738 [ DOI: 10.1109/CVPRW50498.2020.00329 http://dx.doi.org/10.1109/CVPRW50498.2020.00329 ]

Isola P, Zhu J Y, Zhou T H and Efros A A. 2017. Image-to-image translation with conditional adversarial networks//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE: 5967-5976 [ DOI: 10.1109/CVPR.2017.632 http://dx.doi.org/10.1109/CVPR.2017.632 ]

Joslin M and Hao S. 2020. Attributing and detecting fake images generated by known GANs//Proceedings of 2020 IEEE Security and Privacy Workshops (SPW). San Francisco, USA: IEEE: 8-14 [ DOI: 10.1109/SPW50608.2020.00019 http://dx.doi.org/10.1109/SPW50608.2020.00019 ]

Kang X G, Li Y X, Qu Z H and Huang J W. 2012. Enhancing source camera identification performance with a camera reference phase sensor pattern noise. IEEE Transactions on Information Forensics and Security, 7(2): 393-402 [DOI: 10.1109/TIFS.2011.2168214]

Karras T, Aila T, Laine S and Lehtinen J. 2018. Progressive growing of GANs for improved quality, stability, and variation [EB/OL]. [2021-05-28] . https://arxiv.org/pdf/1710.10196.pdf https://arxiv.org/pdf/1710.10196.pdf

Karras T, Laine S and Aila T. 2019. A style-based generator architecture for generative adversarial networks//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE: 4396-4405 [ DOI: 10.1109/CVPR.2019.00453 http://dx.doi.org/10.1109/CVPR.2019.00453 ]

Karras T, Laine S, Aittala M, Hellsten J, Lehtinen J and Aila T. 2020. Analyzing and improving the image quality of styleGAN//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE: 8107-8116 [ DOI: 10.1109/CVPR42600.2020.00813 http://dx.doi.org/10.1109/CVPR42600.2020.00813 ]

Kim D, Jang H U, Mun S M, Choi S and Lee H K. 2018. Median filtered image restoration and anti-forensics using adversarial networks. IEEE Signal Processing Letters, 25(2): 278-282 [DOI: 10.1109/LSP.2017.2782363]

Kingma D P and Ba J. 2015. Adam: a method for stochastic optimization//Proceedings of 2015 International Conference on Learning Representations (ICLR). San Diego, USA

Kirkpatrick J, Pascanu R, Rabinowitz N, Veness J, Desjardins G, Rusu AA, Milan K, Quan J, Ramalho T, Grabska-Barwinska A, Hassabis D, Clopath C, Kumaran D and Hadsell R. 2017. Overcoming catastrophic forgetting in neural networks. Proceedings of the National Academy of Sciences of the United States of America, 114(13): 3521-3526 [DOI: 10.1073/pnas.1611835114]

Ledig C, Theis L, Huszár F, Caballero J, Cunningham A, Acosta A, Aitken A, Tejani A, Totz J, WangZ H and Shi W Z. 2017. Photo-realistic single image super-resolution using a generative adversarial network//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE: 105-114 [ DOI: 10.1109/CVPR.2017.19 http://dx.doi.org/10.1109/CVPR.2017.19 ]

Li B, Shi Y Q and Huang J W. 2008. Detecting doubly compressed JPEG images by using mode based first digit features//Proceedings of the 10th IEEE Workshop on Multimedia Signal Processing. Cairns, Australia: IEEE: 730-735 [ DOI: 10.1109/MMSP.2008.4665171 http://dx.doi.org/10.1109/MMSP.2008.4665171 ]

Li D Z, Wang W, Fan H X and Dong J. 2021. Exploring adversarial fake images on face manifold//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition: IEEE: 5789-5798.

Li H D, Li B, Tan S Q and Huang J W. 2020a. Identification of deep network generated images using disparities in color components. Signal Processing, 174: #107616 [DOI: 10.1016/j.sigpro.2020.107616]

Li L Z, Bao J M, Zhang T, Yang H, Chen D, Wen F and Guo B N. 2020b. Face X-ray for more general face forgery detection//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE: 5000-5009 [ DOI: 10.1109/CVPR42600.2020.00505 http://dx.doi.org/10.1109/CVPR42600.2020.00505 ]

Liu H G, Li X D, Zhou W B, Chen Y F, He Y, Xue H, Zhang W M and Yu N H. 2021. Spatial-phase shallow learning: rethinking face forgery detection in frequency domain//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition: IEEE: 772-781

Liu Z L, Zhu W and Yuan Z Y. 2019. Image instance style transfer combined with fully convolutional network and CycleGAN. Journal of Image and Graphics, 24(8): 1283-1291

刘哲良, 朱玮, 袁梓洋. 2019. 结合全卷积网络与CycleGAN的图像实例风格迁移. 中国图象图形学报, 24(8): 1283-1291) [DOI: 10.11834/jig.180624]

Liu Z W, Miao Z Q, Zhan X H, Wang J Y, Gong B Q and Yu S X. 2019. Large-scale long-tailed recognition in an open world//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE: 2532-2541 [ DOI: 10.1109/CVPR.2019.00264 http://dx.doi.org/10.1109/CVPR.2019.00264 ]

Liu Z Z, Qi X J and Torr P H S. 2020. Global texture enhancement for fake face detection in the wild//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE: 8057-8066 [ DOI: 10.1109/CVPR42600.2020.00808 http://dx.doi.org/10.1109/CVPR42600.2020.00808 ]

Lukas J, Fridrich J and Goljan M. 2006. Digital camera identification from sensor pattern noise. IEEE Transactions on Information Forensics and Security, 1(2): 205-214 [DOI: 10.1109/TIFS.2006.873602]

Luo Y M, Zi H Q, Zhang Q and Kang X G. 2018. Anti-forensics of JPEG compression using generative adversarial networks//Proceedings of the 26th European Signal Processing Conference. Rome, Italy: IEEE: 952-956 [ DOI: 10.23919/EUSIPCO.2018.8553259 http://dx.doi.org/10.23919/EUSIPCO.2018.8553259 ]

Mandelli S, Bonettini N, Bestagini P and Tubaro S. 2020. Training CNNs in presence of JPEG compression: multimedia forensics vs computer vision//Proceedings of 2020 IEEE International Workshop on Information Forensics and Security (WIFS). New York, USA: IEEE: 1-6 [[ 10.1109/WIFS49906.2020.9360903 http://dx.doi.org/[10.1109/WIFS49906.2020.9360903 ]

Marra F, Gragnaniello D, Cozzolino D and Verdoliva L. 2018. Detection of GAN-generated fake images over social networks//Proceedings of 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR). Miami, USA: IEEE: 384-389 [ DOI: 10.1109/MIPR.2018.00084 http://dx.doi.org/10.1109/MIPR.2018.00084 ]

Marra F, Gragnaniello D, Verdoliva L and Poggi G. 2019b. Do GANs leave artificial fingerprints? //Proceedings of 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR). San Jose, USA: IEEE: 506-511 [ DOI: 10.1109/MIPR.2019.00103 http://dx.doi.org/10.1109/MIPR.2019.00103 ]

Marra F, Saltori C, Boato G and Verdoliva L. 2019a. Incremental learning for the detection and classification of GAN-generated images//Proceedings of 2019 IEEE International Workshop on Information Forensics and Security (WIFS). Delft, the Netherlands: IEEE: 1-6 [ DOI: 10.1109/WIFS47025.2019.9035099 http://dx.doi.org/10.1109/WIFS47025.2019.9035099 ]

McCloskey S and Albright M. 2019. Detecting GAN-generated imagery using saturation cues//Proceedings of 2019 IEEE International Conference on Image Processing (ICIP). Taipei, China: IEEE: 4584-4588 [ DOI: 10.1109/ICIP.2019.8803661 http://dx.doi.org/10.1109/ICIP.2019.8803661 ]

Mi Z J, Jiang X H, Sun T F and Xu K. 2020. GAN-generated image detection with self-attention mechanism against GAN generator defect. IEEE Journal of Selected Topics in Signal Processing, 14(5): 969-981 [DOI: 10.1109/JSTSP.2020.2994523]

Mirza M and Osindero S. 2014. Conditional generative adversarial nets [EB/OL]. [2020-11-06] . https://arxiv.org/pdf/1411.1784.pdf https://arxiv.org/pdf/1411.1784.pdf

Mo H X, Chen B L and Luo W Q. 2018. Fake faces identification via convolutional neural network//Proceedings of the 6th ACM Workshop on Information Hiding and Multimedia Security. Innsbruck, Austria: ACM: 43-47 [ DOI: 10.1145/3206004.3206009 http://dx.doi.org/10.1145/3206004.3206009 ]

Nabati M, Navidan H, Shahbazian R, Ghorashi S A and Windridge D. 2020. Using synthetic data to enhance the accuracy of fingerprint-based localization: a deep learning approach. IEEE Sensors Letters, 4(4): 1-4 [DOI: 10.1109/LSENS.2020.2971555]

Nataraj L, Mohammed T M, Manjunath B S, Chandrasekaran S, Flenner A, Bappy J H and Roy-Chowdhury A K. 2019. Detecting GAN generated fake images using co-occurrence matrices. Electronic Imaging, 2019(5): 532-1-532-7 [DOI: 10.2352/ISSN.2470-1173.2019.5.MWSF-532]

Nightingale S J, Wade K A and Watson D G. 2017. Can people identify original and manipulated photos of real-world scenes? Cognitive Research: Principles and Implications, 2(1): #30 [DOI: 10.1186/s41235-017-0067-2]

Odena A, Dumoulin V and Olah C. 2016. Deconvolution and checkerboard artifacts. Distill, 1(10): #e3 [DOI: 10.23915/distill.00003]

Park T, Liu M Y, Wang T C and Zhu J Y. 2019. Semantic image synthesis withspatially-adaptive normalization//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE: 2332-2341 [ DOI: 10.1109/CVPR.2019.00244 http://dx.doi.org/10.1109/CVPR.2019.00244 ]

Peng F, Yin L P, Zhang L B and Long M. 2020. CGR-GAN: CG facial image regeneration for antiforensics based on generative adversarial network. IEEE Transactions on Multimedia, 22(10): 2511-2525 [DOI: 10.1109/TMM.2019.2959443]

Perov I, Gao D H, Chervoniy N, Liu K L, Marangonda S, Umé C, Jiang J, RP L, Zhang S, Wu P Y and Zhang W M. 2020. DeepFaceLab: a simple, flexible and extensible face swapping framework[EB/OL]. [2020-05-20] . https://arxiv.org/pdf/2005.05535v1.pdf https://arxiv.org/pdf/2005.05535v1.pdf

Pevny T, Bas P and Fridrich J. 2010. Steganalysis by subtractive pixel adjacency matrix. IEEE Transactions on information Forensics and Security, 5(2): 215-224 [DOI: 10.1109/TIFS.2010.2045842]

Radford A, Metz L and Chintala S. 2016. Unsupervised representation learning with deep convolutional generative adversarial networks//Proceedings of 2016 International Conference on Learning Representations (ICLR). San Juan, Puerto Rico

Reed S, Akata Z, Yan X C, Logeswaran L, Schiele B and Lee H. 2016. Generative adversarial text to image synthesis//Proceedings of the 33rd International Conference on International Conference on Machine Learning. New York, USA: JMLR. org: 1060-1069

Stamm M C and Liu K J R. 2011. Anti-forensics of digital image compression. IEEE Transactions on Information Forensics and Security, 6(3): 1050-1065 [DOI: 10.1109/TIFS.2011.2119314]

Tolosana R, Vera-Rodriguez R, Fierrez J, Morales A and Ortega-Garcia J. 2020. DeepFakes and beyond: a survey of face manipulation and fake detection. Information Fusion, 64: 131-148 [DOI: 10.1016/j.inffus.2020.06.014]

Verdoliva L. 2020. Media forensics and DeepFakes: an overview. IEEE Journal of Selected Topics in Signal Processing, 14(5): 910-932 [DOI: 10.1109/JSTSP.2020.3002101]

Wang K F, Gou C, Duan Y J, Lin Y L, Zheng X H and Wang F Y. 2017. Generative adversarial networks: the state of the art and beyond. Acta Automatica Sinica, 43(3): 321-332

王坤峰, 苟超, 段艳杰, 林懿伦, 郑心湖, 王飞跃. 2017. 生成式对抗网络GAN的研究进展与展望. 自动化学报, 43(3): 321-332) [DOI: 10.16383/j.aas.2017.y000003]

Wang M, Yang G Y, Li R L, Liang R Z, Zhang S H, Hall P M and Hu S M. 2019. Example-guided style-consistent image synthesis from semantic labeling//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE: 1495-1504 [ DOI: 10.1109/CVPR.2019.00159 http://dx.doi.org/10.1109/CVPR.2019.00159 ]

Wang R, Juefei-Xu F, Ma L, Xie X F, Huang Y H, Wang J and Liu Y. 2020b. FakeSpotter : a simple yet robust baseline for spotting AIsynthesized fake faces//Proceedings of the 29th International Joint Conference on Artificial Intelligence. Yokohama, Japan: [s. n.]: 3444-3451 [ DOI: 10.24963/ijcai.2020/476 http://dx.doi.org/10.24963/ijcai.2020/476 ].

Wang S Y, Wang O, Zhang R, Owens A and Efros A A. 2020a. CNN-generated images are surprisingly easy to spot. . . for now//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE: 8692-8701 [ DOI: 10.1109/CVPR42600.2020.00872 http://dx.doi.org/10.1109/CVPR42600.2020.00872 ]

Wang T C, Liu M Y, Zhu J Y, Tao A, Kautz J and Catanzaro B. 2018. High-resolution image synthesis and semantic manipulation with conditional GANs//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE: 8798-8807 [ DOI: 10.1109/CVPR.2018.00917 http://dx.doi.org/10.1109/CVPR.2018.00917 ]

Wu J Y, Kang X G, Yang J H and Sun W. 2021a. A framework of generative adversarial networks with novel loss for JPEG restoration and anti-forensics. Multimedia Systems, 27: 1075-1089 [DOI: 10.1007/s00530-021-00778-6]

Wu J Y, Liu L, Kang X Q and Sun W. 2020. A generative adversarial network framework for JPEG anti-forensics//Proceedings of 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). Auckland, New Zealand: IEEE: 1442-1447

Wu J Y and Sun W. 2021. Towards multi-operation image anti-forensics with generative adversarial networks. Computers and Security, 100: #102083 [DOI: 10.1016/j.cose.2020.102083]

Wu J Y, Wang Z, Zeng H and Kang X Q. 2019. Multiple-operation image anti-forensics with WGAN-GP framework//Proceedings of 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). Lanzhou, China: IEEE: 1303-1307 [ DOI: 10.1109/APSIPAASC47483.2019.9023173 http://dx.doi.org/10.1109/APSIPAASC47483.2019.9023173 ]

Xie H, Ni J Q and Shi Y Q. 2021. Dual-domain generative adversarial network for digital image operation anti-forensics. IEEE Transactions on Circuits and Systems for Video Technology: #9383304 [DOI: 10.1109/TCSVT.2021.3068294]

Yang R, Luo W Q and Huang J W. 2013. Multimedia forensics. Scientia Sinica Informationis, 43(12): 1654-1672

杨锐, 骆伟祺, 黄继武. 2013. 多媒体取证. 中国科学: 信息科学, 43(12): 1654-1672) [DOI: 10.1360/N112013-00059]

Yu N, Davis L and Fritz M. 2018. Attributing fake images to GANs: learning and analyzing GAN fingerprints//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, Korea (South): IEEE: 7555-7565 [ DOI: 10.1109/ICCV.2019.00765 http://dx.doi.org/10.1109/ICCV.2019.00765 ]

Zhang H, Goodfellow I, Metaxas D and Odena A. 2019a. Self-attention generative adversarial networks//Proceedings of the 36th International Conference on Machine Learning. Long Beach, USA: PMLR: 7354-7363

Zhang H, Xu T, Li H S, Zhang S T, Wang X G, Huang X L and Metaxas D. 2017. StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE: 5908-5916 [ DOI: 10.1109/ICCV.2017.629 http://dx.doi.org/10.1109/ICCV.2017.629 ]

Zhang X, Karaman S and Chang S F. 2019b. Detecting and simulating artifacts in GAN fake images//Proceedings of 2019 IEEE International Workshop on Information Forensics and Security (WIFS). Delft, the Netherlands: IEEE: 1-6 [ DOI: 10.1109/WIFS47025.2019.9035107 http://dx.doi.org/10.1109/WIFS47025.2019.9035107 ]

Zhang X L, Fang Z and Zhang X P. 2015. Forgery detection via inter-channel correlation of CFA images. Journal of Applied Sciences, 33(1): 87-94

张晓琳, 方针, 张新鹏. 2015. 利用通道间相关性的CFA图像盲取证. 应用科学学报, 33(1): 87-94) [DOI: 10.3969/j.issn.0255-8297.2015.01.010]

Zhao X W, Chen C and Stamm M C. 2021. A transferable anti-Forensic attack on forensic CNNs using a generative adversarial network [EB/OL]. [2021-01-23] . http://arxiv.org/pdf/2101.09568.pdf http://arxiv.org/pdf/2101.09568.pdf

Zhu J Y, Park T, Isola P and Efros A A. 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE: 2242-2251 [ DOI: 10.1109/ICCV.2017.244 http://dx.doi.org/10.1109/ICCV.2017.244 ]

Zou H, Yang P P, Ni R R and Zhao Y. 2021. Anti-forensics of image contrast enhancement based on generative adversarial network. Security and Communication Networks, 2021: #6663486 [DOI: 10.1155/2021/6663486]