FakeBuster: A DeepFakes Detection Tool for Video Conferencing Scenarios

TL;DR

FakeBuster is a deep learning-based tool designed to detect manipulated or spoofed videos during video conferencing, enhancing security and trust in virtual meetings across various platforms.

Contribution

It introduces a standalone DeepFake detection tool using a 3D CNN trained on diverse datasets, tailored for real-time video conferencing scenarios.

Findings

Effective detection of DeepFakes in video conferencing environments

Generalizes well across different datasets and perturbations

Independent of specific video conferencing platforms

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.