Submitted by Andreas Rössler.

Submission data

Full nameRecasting c40
DescriptionSee FaceForensics ++ paper. A classifier based on recasting trained on the c40 compressed data.
Publication titleRecasting residual-based local descriptors as convolutional neural networks: an application to image forgery detection
Publication authorsDavide Cozzolino, Giovanni Poggi, and Luisa Verdoliva
Publication venueACM Workshop on Information Hiding and Multimedia Security
Publication URLhttps://arxiv.org/pdf/1703.04615.pdf
Input Data TypesUses Face Detection
Programming language(s)Python, Keras
HardwareIntel Xeon 6140, 2080ti
Submission creation date29 Aug, 2019
Last edited29 Aug, 2019

Binary Classification v3

InfoDeepfakesFace2FaceFaceSwapNeuralTexturesPristineTotal
0.8550.6790.7380.7800.3440.552