This table lists the benchmark results for the Binary Classification scenario.


Method InfoDeepfakesFace2FaceFaceSwapPristineTotal
sort bysort bysort bysort bysorted by
Xception (FaceForensics++)permissive0.8820.7150.7180.7970.783
Andreas Rössler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, Matthias Nießner: FaceForensics++. arxiv
Expert Human (Justus Thies)0.7730.3210.6890.8800.726
XceptionFull (FaceForensics++)permissive0.7550.7590.6990.6970.719
Andreas Rössler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, Matthias Nießner: FaceForensics++. arxiv
MesoNet c400.7000.4890.6120.8230.707
Darius Afchar, Vincent Nozick, Junichi Yamagishi, Isao Echizen: MesoNet: a Compact Facial Video Forgery Detection Network. WIFS 2018
Bayar c230.8820.7300.6500.6140.684
B. Bayar and M. Stamm: A deep learning approach to universal image manipulation detection using a new convolutional layer. ACM Workshop on Information Hiding and Multimedia Security
Rahmouni c400.6910.4010.4470.7090.607
N. Rahmouni, V. Nozick, J. Yamagishi, and I. Echizen: Distinguishing computer graphics from natural images using convolution neural networks. IEEE Workshop on Information Forensics and Security
Recast c230.8360.8470.8250.3260.581
D. Cozzolino, G. Poggi, and L. Verdoliva: Recasting residual-based local descriptors as convolutional neural networks: an application to image forgery detection. ACM Workshop on Information Hiding and Multimedia Security,