A Robust GAN-Generated Face Detection Method Based on Dual-Color Spaces and an Improved Xception

• Published in: IEEE transactions on circuits and systems for video technology Vol. 32; no. 6; pp. 3527 - 3538
• Main Authors: Chen, Beijing, Liu, Xin, Zheng, Yuhui, Zhao, Guoying, Shi, Yun-Qing
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.06.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Blurring; Color; color space; Convolution; Convolutional neural networks; Face detection; Face recognition; Faces; Feature extraction; Generated face; generative adversarial network; Generative adversarial networks; Image color analysis; Image compression; Modules; Multilayers; Performance degradation; Robustness; Xception

In recent years, generative adversarial networks (GANs) have been widely used to generate realistic fake face images, which can easily deceive human beings. To detect these images, some methods have been proposed. However, their detection performance will be degraded greatly when the testing samples...