Recurrent Convolutional Strategies for Face Manipulation Detection in Videos

TL;DR

This paper introduces a recurrent convolutional approach leveraging temporal information for detecting manipulated faces in videos, achieving state-of-the-art accuracy on benchmark datasets.

Contribution

It develops and optimizes recurrent convolutional strategies combined with domain-specific preprocessing for improved video-based face manipulation detection.

Findings

Achieved up to 4.55% accuracy improvement over previous methods.

Effectively detects Deepfake, Face2Face, and FaceSwap manipulations.

Validated on FaceForensics++ dataset.

Abstract

The spread of misinformation through synthetically generated yet realistic images and videos has become a significant problem, calling for robust manipulation detection methods. Despite the predominant effort of detecting face manipulation in still images, less attention has been paid to the identification of tampered faces in videos by taking advantage of the temporal information present in the stream. Recurrent convolutional models are a class of deep learning models which have proven effective at exploiting the temporal information from image streams across domains. We thereby distill the best strategy for combining variations in these models along with domain specific face preprocessing techniques through extensive experimentation to obtain state-of-the-art performance on publicly available video-based facial manipulation benchmarks. Specifically, we attempt to detect Deepfake, Face2Face and FaceSwap tampered faces in video streams. Evaluation is performed on the recently introduced FaceForensics++ dataset, improving the previous state-of-the-art by up to 4.55% in accuracy.