Deepfake Detection using Spatiotemporal Convolutional Networks

TL;DR

This paper introduces a deepfake detection approach leveraging spatiotemporal convolutional networks that analyze both spatial and temporal features, outperforming existing frame-based methods on the Celeb-DF dataset.

Contribution

The paper presents a novel spatiotemporal convolutional network framework for deepfake detection and provides a benchmark demonstrating its superior performance over frame-based methods.

Findings

Spatiotemporal methods outperform frame-based detection.

Benchmark on Celeb-DF dataset shows improved accuracy.

Code is publicly available for reproducibility.

Abstract

Better generative models and larger datasets have led to more realistic fake videos that can fool the human eye but produce temporal and spatial artifacts that deep learning approaches can detect. Most current Deepfake detection methods only use individual video frames and therefore fail to learn from temporal information. We created a benchmark of the performance of spatiotemporal convolutional methods using the Celeb-DF dataset. Our methods outperformed state-of-the-art frame-based detection methods. Code for our paper is publicly available at https://github.com/oidelima/Deepfake-Detection.