FakeBuster: A DeepFakes Detection Tool for Video Conferencing Scenarios

Authors: Vineet Mehta, Parul Gupta, Ramanathan Subramanian, Abhinav Dhall

Published: 2021-01-09 09:06:08+00:00

AI Summary

FakeBuster is a standalone deep learning-based tool for detecting deepfakes in video conferencing scenarios. It uses a 3D convolutional neural network trained on a diverse dataset to predict video segment-wise fakeness scores, offering a user-friendly interface for real-time detection.

Abstract

This paper proposes a new DeepFake detector FakeBuster for detecting impostors during video conferencing and manipulated faces on social media. FakeBuster is a standalone deep learning based solution, which enables a user to detect if another person's video is manipulated or spoofed during a video conferencing based meeting. This tool is independent of video conferencing solutions and has been tested with Zoom and Skype applications. It uses a 3D convolutional neural network for predicting video segment-wise fakeness scores. The network is trained on a combination of datasets such as Deeperforensics, DFDC, VoxCeleb, and deepfake videos created using locally captured (for video conferencing scenarios) images. This leads to different environments and perturbations in the dataset, which improves the generalization of the deepfake network.