Deep fake face detection method based on generative adversarial network

The invention discloses a deep fake face detection method based on a generative adversarial network, and relates to the field of big data AI image anti-counterfeiting. According to the deep fake face detection method based on the generative adversarial network, the deep fake face detection method based on the generative adversarial network comprises the following steps of S1, pre-training a discriminator; s2, training the GAN network; and S3, identifying the authenticity of the image. According to the deep fake face detection method based on the generative adversarial network, only a real face image is used in training, and a generator can reconstruct input without noise in reasoning detection by fully fitting spatial distribution of a real sample, so that an attack defense effect is achieved; the generator uses the deviation as a decision rule for judging counterfeit detection, and any counterfeit mode can be regarded as abnormity. 本发明公开一种基于生成对抗网络的深度伪造人脸检测方法，涉及大数据AI图像防伪领域。该基于生成对抗网络的深度伪造人脸检测方法，所述基于生成对抗网络的深度伪造