Abstract
AI image tampering technology - DeepFakes has a huge impact on the authenticity of video information in the network, making “seeing is believing” no longer credible. Finding effective methods for detecting DeepFakes is very important. The existing detection methods mostly rely on artificially designed features. This paper first proposes an adaptive deep learning detection model - DFDM for DeepFakes. DFDM uses deep learning networks to adaptively extract features of forgery images, which is efficient when facing a large number of samples and avoid the limitations of traditional detection methods. DFDM refers to the structure of steganalysis and forensic networks and pays attention to the anomaly of pixel distribution in images. DFDM can identify the anomaly of image texture features better than the general classification network. DFDM abandons the residual processing in the steganographic detection network, and designs a custom convolution kernel suitable for identifying image texture features to improve the accuracy of model detection. In the model network structure, DFDM replaces the mean pooling layer in steganalysis networks with the max-pooling layer, maximally retaining the image texture features. The simulation results show that the detection accuracy of DFDM for full-face replacement reaches 0.99, and the detection accuracy for partial-face replacement reaches 0.98.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Miller, J.: The realities and challenges of legislating DeepFakes. Signal 74(1) (2019)
Konkel, F.: AI, DeepFakes and the other tech threats that vex intel leaders. Nextgov.com (Online) (2019)
Yi, X., Walia, E., Babyn, P.: Generative adversarial network in medical imaging: a review. Med. Image Anal. 58, 101552 (2019)
Sannidhan, M.S., Ananth Prabhu, G., Robbins, D.E., Shasky, C.: Evaluating the performance of face sketch generation using generative adversarial networks. Pattern Recogn. Lett. 128, 452–458 (2019)
Madsen, S.L., Dyrmann, M., Jørgensen, R.N., Karstoft, H.: Generating artificial images of plant seedlings using generative adversarial networks. Biosyst. Eng. 187, 147–159 (2019)
Yang, Z., Yu, Y.: Research of DeepFakes analysis and detection methods. J. Beijing Univ. Posts Telecommun. (2019)
Barani, M.J., Valandar, M.Y., Ayubi, P.: A new digital image tamper detection algorithm based on integer wavelet transform and secured by encrypted authentication sequence with 3D quantum map. Optik 187, 205–222 (2019)
Swaraja, K., Meenakshi, K., Kora, P.: An optimized blind dual medical image watermarking framework for tamper localization and content authentication in secured telemedicine. Biomed. Signal Process. Control 55, 101665 (2020)
Brunese, L., Mercaldo, F., Reginelli, A., Santone, A.: Radiomic features for medical images tamper detection by equivalence checking. Procedia Comput. Sci. 159, 1795–1802 (2019)
Brito, C., Machado, A., Sousa, A.: Electrocardiogram beat-classification based on a ResNet network. Stud. Health Technol. Inf. 264, 55–59 (2019)
Khan, R.U., Zhang, X., Kumar, R.: Analysis of ResNet and GoogleNet models for malware detection. J. Comput. Virol. Hacking Tech. 15(1), 29–37 (2019)
Li, Y., Chang, M.C., Lyu, S.: In Ictu Oculi: exposing AI created fake videos by detecting eye blinking (2018)
Yang, X., Li, Y., Lyu, S.: Exposing deep fakes using inconsistent head poses (2018)
Gu, Y., He, M., Nagano, K., Li, H.: Protecting world leaders against deep fakes (2019)
Hasan, H.R., Salah, K.: Combating deepfake videos using blockchain and smart contracts. IEEE Access 7, 41596–41606 (2019)
Agarwal, S., Varshney, L.R.: Limits of deepfake detection: a robust estimation viewpoint (2019)
Zhan, Y., Chen, Y., Zhang, Q., Kang, X.: Image forensics based on transfer learning and convolutional neural network. In: IH&MMSec (2017)
Ye, J.C., Huang, X.S., Wang, S.L.: Exploation on nsF5 Steganalysis based on CNN. Commun. Technol. 52(03), 696–700 (2019)
Pu, Y.: Research on digital image steganography algorithm based on deep learning. Beijing University of Posts and Telecommunications (2019)
Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., Nießner, M.: FaceForensics+ +: learning to detect manipulated facial images (2019)
Huang, T.S., Schreiber, W.F., Tretiak, O.J.: Image processing. Proc. IEEE 59(11), 1586–1609 (1971)
Fang, Z., et al.: Abnormal event detection in crowded scenes based on deep learning. Multimedia Tools Appl. 75(22), 14617–14639 (2016). https://doi.org/10.1007/s11042-016-3316-3
Wan, Z., Xiong, N., Ghani, N., Vasilakos, A.V., Zhou, L.: Adaptive unequal protection for wireless video transmission over IEEE 802.11 e networks. Multimedia Tools Appl. 72(1), 541–571 (2014)
Yang, J., et al.: A fingerprint recognition scheme based on assembling invariant moments for cloud computing communications. IEEE Syst. J. 5(4), 574–583 (2011)
Guo, Y., Li, C., Liu, Q.: R2N: a novel deep learning architecture for rain removal from single image. Comput. Mater. Continua 58(3), 829–843 (2019)
Hao, W., Liu, Q., Liu, X.: A review on deep learning approaches to image classification and object segmentation. Comput. Mater. Continua 60(2), 575–597 (2019)
Xianyu, W., Luo, C., Zhang, Q., Zhou, J., Yang, H., Li, Y.: Text detection and recognition for natural scene images using deep convolutional neural networks. Comput. Mater. Continua 61(1), 289–300 (2019)
Acknowledgements
This work is supported by the National Key R&D Program of China (2017YFB0802703), Research on the education mode for complicate skill students in new media with cross specialty integration (22150117092), Major Scientific and Technological Special Project of Guizhou Province (20183001), Open Foundation of Guizhou Provincial Key Laboratory of Public Big Data (2018BDKFJJ014), Open Foundation of Guizhou Provincial Key Laboratory of Public Big Data (2018BDKFJJ019) and Open Foundation of Guizhou Provincial Key Laboratory of Public Big Data (2018BDKFJJ022).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zeng, Y., Guo, X., Yang, Y., Zhan, R. (2020). DFDM - A DeepFakes Detection Model Based on Steganography Forensic Network. In: Sun, X., Wang, J., Bertino, E. (eds) Artificial Intelligence and Security. ICAIS 2020. Communications in Computer and Information Science, vol 1253. Springer, Singapore. https://doi.org/10.1007/978-981-15-8086-4_51
Download citation
DOI: https://doi.org/10.1007/978-981-15-8086-4_51
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-8085-7
Online ISBN: 978-981-15-8086-4
eBook Packages: Computer ScienceComputer Science (R0)