Key points are not available for this paper at this time.
This paper presents a method to automatically and efficiently detect face tampering in videos, and particularly focuses on two recent techniques used to generate hyper-realistic forged videos: Deepfake and Face2Face. Traditional image forensics techniques are usually not well suited to videos due to the compression that strongly degrades the data. Thus, this paper follows a deep learning approach and presents two networks, both with a low number of layers to focus on the mesoscopic properties of images. We evaluate those fast networks on both an existing dataset and a dataset we have constituted from online videos. The tests demonstrate a very successful detection rate with more than 98% for Deepfake and 95% for Face2Face.
Building similarity graph...
Analyzing shared references across papers
Loading...
Darius Afchar
Vincent Nozick
Junichi Yamagishi
National Institute of Informatics
Université Gustave Eiffel
École nationale des ponts et chaussées
National Institute of Informatics
Building similarity graph...
Analyzing shared references across papers
Loading...
Afchar et al. (Sat,) studied this question.
synapsesocial.com/papers/6a01ec69bd6301933f5cd0f4 — DOI: https://doi.org/10.1109/wifs.2018.8630761