3D CNN Architectures and Attention Mechanisms for Deepfake Detection

Abstract

AbstractManipulated 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. Toward 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. In addition, and toward a more robust detection, we investigate the effectiveness of attention mechanisms in this context. Such mechanisms are introduced in CNN architectures in order to ensure that robust features are being learnt. We test two attention mechanisms, namely SE-block and Non-local networks. 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, (b) each manipulation technique individually, as well as (c) the veracity of videos pertaining to manipulation techniques not included in the train set.