A video is worth more than 1000 lies. Comparing 3DCNN approaches for detecting deepfakes

Manipulated images and videos have become increasingly realistic due to the tremendous progress of deep convolutional neural networks (CNNs). While technically intriguing, such progress raises a number of social concerns related to the advent and spread of fake information and fake news. Such concerns necessitate the introduction of robust and reliable methods for fake image and video detection. Towards this in this work, we study the ability of state of the art video CNNs including 3D ResNet, 3D ResNeXt, and I3D in detecting manipulated videos. We present related experimental results on videos tampered by four manipulation techniques, as included in the FaceForensics++ dataset. We investigate three scenarios, where the networks are trained to detect (a) all manipulated videos, as well as (b) separately each manipulation technique individually. Finally and deviating from previous works, we conduct cross-manipulation results, where we (c) detect the veracity of videos pertaining to manipulation-techniques not included in the train set. Our findings clearly indicate the need for a better understanding of manipulation methods and the importance of designing algorithms that can successfully generalize onto unknown manipulations.