A Dual-Branch Fusion Model for Deepfake Detection Using Video Frames and Microexpression Features

TL;DR

This paper introduces a new deepfake detection method that combines video frames and microexpression features to achieve high accuracy.

Contribution

A dual-branch fusion model that integrates 3D ResNet18 and a transformer for deepfake detection.

Findings

The model achieves 99.81% accuracy on the FaceForensics++ dataset.

It obtains a perfect ROC-AUC score of 100%.

The method outperforms existing state-of-the-art deepfake detection approaches.

Abstract

Deepfake detection has become a critical issue due to the rise of synthetic media and its potential for misuse. In this paper, we propose a novel approach to deepfake detection by combining video frame analysis with facial microexpression features. The dual-branch fusion model utilizes a 3D ResNet18 for spatiotemporal feature extraction and a transformer model to capture microexpression patterns, which are difficult to replicate in manipulated content. We evaluate the model on the widely used FaceForensics++ (FF++) dataset and demonstrate that our approach outperforms existing state-of-the-art methods, achieving 99.81% accuracy and a perfect ROC-AUC score of 100%. The proposed method highlights the importance of integrating diverse data sources for deepfake detection, addressing some of the current limitations of existing systems.

Figures