Deepfake Forensics via An Adversarial Game. (arXiv:2103.13567v2 [cs.CV] UPDATED)

With the progress in AI-based facial forgery (i.e., deepfake), people are
increasingly concerned about its abuse. Albeit effort has been made for
training classification (also known as deepfake detection) models to recognize
such forgeries, existing models suffer from poor generalization to unseen
forgery technologies and high sensitivity to changes in image/video quality. In
this paper, we advocate adversarial training for improving the generalization
ability to both unseen facial forgeries and unseen image/video qualities. We
believe training with samples that are …

adversarial deepfake forensics game