计算机科学 ›› 2023, Vol. 50 ›› Issue (6): 216-224.doi: 10.11896/jsjkx.220400268
王金伟1,2,3, 曾可慧1, 张家伟1, 罗向阳3, 马宾4
WANG Jinwei1,2,3, ZENG Kehui1, ZHANG Jiawei1, LUO Xiangyang3, MA Bin4
摘要: 生成式对抗网络(GAN)的快速发展使其在图像生成领域取得了前所未有的成功。StyleGAN等新型GAN的出现使得生成的图像更真实且具有欺骗性,对国家安全、社会稳定和个人隐私都构成了较大威胁。文中提出了一种基于空频联合的双流卷积神经网络的检测模型。鉴于GAN图像在生成过程中因上采样操作在频谱上留下了清晰可辨的伪影,设计了可学习的频率域滤波核以及频率域网络来充分学习并提取频率域特征。为了减弱图像变换至频域过程中丢弃部分信息而带来的影响,同样设计了空间域网络来学习图像内容本身具有差异化的空间域特征,最终将两种特征融合来实现对GAN生成人脸图像的检测。在多个数据集上的实验结果表明,所提模型在高质量生成数据集上的检测精度及在跨数据集的泛化性上都优于现有算法,且对于JPEG压缩、随机剪裁、高斯模糊等图像变换具有更强的鲁棒性。不仅如此,所提方案在GAN生成的局部人脸数据集上也有不错表现,进一步证明了所提模型有着更好的通用性以及更加广泛的应用前景。
中图分类号:
[1]STUPP C.Fraudsters used AI to mimic CEO's voice in unusual cybercrime case[J].The Wall Street Journal,2019,30(8). [2]KARRAS T,AILA T,LAINE S,et al.Progressive growing of gans for improved quality,stability,and variation[J].arXiv:1710.10196,2017. [3]MARRA F,GRAGNANIELLO D,COZZOLINO D,et al.Detection of GAN-generated fake images over social networks[C]//2018 IEEE Conference on Multimedia Information Processing and Retrieval(MIPR).IEEE,2018:384-389. [4]MCCLOSKEY S,ALBRIGHT M.Detecting GAN-generatedimagery using saturation cues[C]//2019 IEEE International Conference on Image Processing(ICIP).IEEE,2019:4584-4588. [5]BARNI M,KALLAS K,NOWROOZI E,et al.CNN detection of GAN-generated face images based on cross-band co-occurrences analysis[C]//2020 IEEE International Workshop on Information Forensics and Security(WIFS).IEEE,2020:1-6. [6]GUO Z,YANG G,CHEN J,et al.Fake face detection via adaptive manipulation traces extraction network[J].Computer Vision and Image Understanding,2021,204:103170. [7]FRANK J,EISENHOFER T,SCHÖNHERR L,et al.Levera-ging frequency analysis for deep fake image recognition[C]//International Conference on Machine Learning.PMLR,2020:3247-3258. [8]LI H,LI B,TAN S,et al.Detection of deep network generated images using disparities in color components[J].arXiv:1808.07276. [9]MO H,CHEN B,LUO W.Fake faces identification via convolutional neural network[C]//Proceedings of the 6th ACM Workshop on Information Hiding and Multimedia Security.2018:43-47. [10]NATARAJ L,MOHAMMED T M,MANJUNATH B S,et al.Detecting GAN generated fake images using co-occurrence matrices[J].Electronic Imaging,2019(5):532-1-532-7. [11]FU Y,SUN T,JIANG X,et al.Robust gan-face detection based on dual-channel cnn network[C]//2019 12th International Congress on Image and Signal Processing,BioMedical Engineering and Informatics(CISP-BMEI).IEEE,2019:1-5. [12]WANG S Y,WANG O,ZHANG R,et al.Cnn-generated images are surprisingly easy to spot…for now[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:8695-8704. [13]WANG S Y,WANG O,ZHANG R,et al.Cnn-generated images are surprisingly easy to spot for now[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:8695-8704. [14]AGARWAL S,GIRDHAR N,RAGHAV H.A Novel Neural Model based Framework for Detection of GAN Generated Fake Images[C]//2021 11th International Conference on Cloud Computing,Data Science & Engineering(Confluence).IEEE,2021:46-51. [15]BONETTINI N,BESTAGINI P,MILANI S,et al.On the use of Benford's law to detect GAN-generated images[C]//2020 25th International Conference on Pattern Recognition(ICPR).IEEE,2020:5495-5502. [16]DURALL R,KEUPER M,KEUPER J.Watch your up-convolution:Cnn based generative deep neural networks are failing to reproduce spectral distributions[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:7890-7899. [17]HE P S,LI W C,ZHANG J Y,et al.Overview of passive forensics and anti-forensics techniques for GAN-generated image[J].Journal of Image and Graphics,2022,27(1):0088-0110. [18]RADFORD A,METZ L,CHINTALA S.Unsupervised representation learning with deep convolutional generative adversarial networks[J].arXiv:1511.06434,2015. [19]ODENA A,DUMOULIN V,OLAH C.Deconvolution andcheckerboard artifacts[J].Distill,2016,1(10):e3. [20]ZHANG X,KARAMAN S,CHANG S F.Detecting and simulating artifacts in gan fake images[C]//2019 IEEE International Workshop on Information Forensics and Security(WIFS).IEEE,2019:1-6. [21]LI C L,RAVANBAKHSH S,POCZOS B.Annealing Gaussian into ReLU:a new sampling strategy for leaky-ReLU RBM[J].arXiv:1611.03879,2016. [22]KARRAS T,LAINE S,AITTALA M,et al.Analyzing and improving the image quality of stylegan[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:8110-8119. [23]KARRAS T,LAINE S,AILA T.A style-based generator architecture for generative adversarial networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:4401-4410. [24]ARJOVSKY M,CHINTALA S,BOTTOU L.Wasserstein ge-nerative adversarial networks[C]//International Conference on Machine Learning.PMLR,2017:214-223. [25]BERTHELOT D,SCHUMM T,METZ L.Began:Boundaryequilibrium generative adversarial networks[J].arXiv:1703.10717,2017. [26]MAO X,LI Q,XIE H,et al.Least squares generative adversarial networks[C]//Proceedings of the IEEE International Confe-rence on Computer Vision.2017:2794-2802. [27]SUN Y,CHEN Y,WANG X,et al.Deeplearning face representation by joint identification-verification[J/OL].Advances in Neural Information Processing Systems,2014,27.https://proceedings.neurips.cc/paper/2014/hash/e5e63da79fcd2bebbd7cb8bf1c1d0274-Abstract.html. [28]CHEN B,JU X,XIAO B,et al.Locally GAN-generated face detection based on an improved Xception[J].Information Sciences,2021,572:16-28. |
|