Deepfake Video Detection Based on EfficientNet-V2 Network. (15th April 2022)

• Record Type: Journal Article
• Authors: Deng, Liwei; Suo, Hongfei; Li, Dongjie
• Other Names: Vessio Gennaro Academic Editor.
• Is Part Of: Computational intelligence and neuroscience. Volume 2022(2022)
• Publication Date: 2022-04-15
• Subjects: Neurosciences -- Data processing -- Periodicals; Computational intelligence -- Periodicals; Computational neuroscience -- Periodicals; 612.80285
• DOI: 10.1155/2022/3441549
• Languages: English
• ISSNs: 1687-5265

Abstract

Abstract : As technology advances and society evolves, deep learning is becoming easier to operate. Many unscrupulous people are using deep learning technology to create fake pictures and fake videos that seriously endanger the stability of the country and society. Examples include faking politicians to make inappropriate statements, using face-swapping technology to spread false information, and creating fake videos to obtain money. In view of this social problem, based on the original fake face detection system, this paper proposes using a new network of EfficientNet-V2 to distinguish the authenticity of pictures and videos. Moreover, our method was used to deal with two current mainstream large-scale fake face datasets, and EfficientNet-V2 highlighted the superior performance of the new network by comparing the existing detection network with the actual training and testing results. Finally, based on improving the accuracy of the detection system in distinguishing real and fake faces, the actual pictures and videos are detected, and an excellent visualization effect is achieved.