Detecting Forged Facial Videos using convolutional neural network
This addresses the issue of video forgery detection for online platforms, but it is incremental as it builds on existing CNN methods with optimizations.
The paper tackles the problem of detecting forged facial videos in online content by proposing a smaller convolutional neural network, achieving state-of-the-art performance on the FaceForensics dataset with both frame-based and video-based results.
In this paper, we propose to detect forged videos, of faces, in online videos. To facilitate this detection, we propose to use smaller (fewer parameters to learn) convolutional neural networks (CNN), for a data-driven approach to forged video detection. To validate our approach, we investigate the FaceForensics public dataset detailing both frame-based and video-based results. The proposed method is shown to outperform current state of the art. We also perform an ablation study, analyzing the impact of batch size, number of filters, and number of network layers on the accuracy of detecting forged videos.