Exposing DeepFake Videos By Detecting Face Warping Artifacts

11/01/2018

∙

by   Yuezun Li, et al.

∙

0

∙

share

In this work, we describe a new deep learning based method that can effectively distinguish AI-generated fake videos (referred to as DeepFake videos hereafter) from real videos. Our method is based on the observations that current DeepFake algorithm can only generate images of limited resolutions, which need to be further warped to match the original faces in the source video. Such transforms leave distinctive artifacts in the resulting DeepFake videos, and we show that they can be effectively captured by convolutional neural networks. Our method is evaluated on a set of DeepFake videos for its effectiveness in practice.