Generate Fake Image and Detection
Generate Fake Image and Detection
Generate Fake Image
-
L. Zhao, C. Chen and J. Huang, “Deep Learning-based Forgery Attack on Document Images”, IEEE Transactions on Image Processing, Accepted Aug. 2021
Fake Image Detection
-
[JSTSP, 2020] Mi, Z., Jiang, X., Sun, T., & 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.
-
With Generative Adversarial Networks (GAN)achieving realistic image generation, fake image detection research has become an imminent need. In this paper, a novel detection algorithm is designed to exploit the structural defect in GAN, taking advantage of the most vulnerable link in GAN generators – the Up-s amplingprocess conducted by the Transposed Convolution operation. The Transposed Convolution in the process will cause the lack of global information in the generated images. Therefore, the Self-Attention mechanism is adopted correspondingly, equipping the algorithm with a much better comprehension of the global information than the other current work adopting pure CNN network, which is reflected in the significant increase in the detection accuracy. With the thorough comparison to the current work and corresponding careful analysis, it is verified that our proposed algorithm outperforms other current works in the field. Also, with experiments conducted on other image-generation categories and images undergone usual real-life post-processing methods, our proposed algorithm shows decent robustness for various categories of imagesunder different reality circumstances, rather than restricted by image types and pure laboratory situation.
-
随着生成对抗网络 (GAN) 实现逼真的图像生成，假图像检测研究已成为迫在眉睫的需求。在本文中，设计了一种新颖的检测算法来利用 GAN 中的结构缺陷，利用 GAN 生成器中最脆弱的环节——由转置卷积操作进行的 Up-s 采样过程。过程中的转置卷积会导致生成的图像缺乏全局信息。因此，相应地采用了Self-Attention机制，使算法比目前采用纯CNN网络的其他工作更好地理解全局信息，这体现在检测精度的显着提高上。通过与当前工作的彻底比较和相应的仔细分析，验证了我们提出的算法优于该领域的其他当前工作。此外，通过对其他图像生成类别和经过通常现实生活后处理方法的图像进行的实验，我们提出的算法在不同的现实环境下对各种类别的图像表现出良好的鲁棒性，而不受图像类型和纯实验室情况的限制。
-
-
[IEEE TMM, 2020] Beijing Chen, Weijin Tan, Gouenou Coatrieux, Yuhui Zheng, and Yun-Qing Shi, “A serial image copy-move forgery localization scheme with source/target distinguishment,” IEEE Transactions on Multimedia. 2020. Online. DOI: 10.1109/TMM.2020.3026868.
-
Juan Hu, Xin Liao, Wei Wang, and Zheng Qin, “Detecting compressedDeepfake videos in social networks using frame-temporality two-streamconvolutional network”, IEEE Transactionson Circuits and Systems for Video Technology, DOI:10.1109/TCSVT.2021.3074259, 2021.
-
H. Wu and J. Zhou, "GIID-Net: Image Inpainting Detection Network via Neural Architecture Search and Attention," in IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2021.3075039.
-
Daichi Zhang, Chenyu Li, Fanzhao Lin, Dan Zeng, Shiming Ge*. Detecting Deepfake Videos with Temporal Dropout 3DCNN. Accepted by International Joint Conference on Artificial Intelligence (IJCAI), 2021.
-
Q Ying, Z Qian*, HZhou, X Zhang, H Xu, S Li,From Image to Imuge: Immunized ImageGeneration, ACM multimedia 2021
感觉这篇的结果很有意思，可能会成为研究的点。
-
Cao, S., Zou, Q., Mao, X., & Wang, Z. (2021). Metric Learning for Anti-Compression Facial Forgery Detection. http://arxiv.org/abs/2103.08397
-
Y. Rao, and J. Ni, “Self-supervised Domain Adaptation for Forgery Localization of JPEG Compressed Images,” IEEE International Conference on Computer Vision (ICCV), Oral, 2021.
-
CAT-NET
Kwon, M.-J., Nam, S.-H., Yu, I.-J., Lee, H.-K., & Kim, C. (2021). Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization. http://arxiv.org/abs/2108.12947
Image Inpainting
-
H. Wu and J. Zhou, "Privacy Leakage of SIFT Features via Deep Generative Model Based Image Reconstruction," in IEEE Transactions on Information Forensics and Security, vol. 16, pp. 2973-2985, 2021, doi: 10.1109/TIFS.2021.3070427.
