MRI-GAN: A Generalized Approach to Detect DeepFakes using Perceptual Image Assessment
This addresses the challenge of identifying synthetic media for security and verification purposes, but the results are incremental as the proposed method underperforms a baseline.
They tackled the problem of detecting DeepFake videos by developing a GAN-based framework called MRI-GAN that uses perceptual image differences, achieving 74% test accuracy on a benchmark dataset, while a simpler model reached 91% accuracy.
DeepFakes are synthetic videos generated by swapping a face of an original image with the face of somebody else. In this paper, we describe our work to develop general, deep learning-based models to classify DeepFake content. We propose a novel framework for using Generative Adversarial Network (GAN)-based models, we call MRI-GAN, that utilizes perceptual differences in images to detect synthesized videos. We test our MRI-GAN approach and a plain-frames-based model using the DeepFake Detection Challenge Dataset. Our plain frames-based-model achieves 91% test accuracy and a model which uses our MRI-GAN framework with Structural Similarity Index Measurement (SSIM) for the perceptual differences achieves 74% test accuracy. The results of MRI-GAN are preliminary and may be improved further by modifying the choice of loss function, tuning hyper-parameters, or by using a more advanced perceptual similarity metric.