How Do Deepfakes Move? Motion Magnification for Deepfake Source Detection
This addresses the challenge of deepfake detection for security and media integrity, offering a method that is incremental by combining deep and traditional motion magnification techniques.
The paper tackled the problem of detecting deepfake videos and identifying their source generators by analyzing subtle motion differences, achieving video source detection accuracies of 97.17% and 94.03% on two datasets.
With the proliferation of deep generative models, deepfakes are improving in quality and quantity everyday. However, there are subtle authenticity signals in pristine videos, not replicated by SOTA GANs. We contrast the movement in deepfakes and authentic videos by motion magnification towards building a generalized deepfake source detector. The sub-muscular motion in faces has different interpretations per different generative models which is reflected in their generative residue. Our approach exploits the difference between real motion and the amplified GAN fingerprints, by combining deep and traditional motion magnification, to detect whether a video is fake and its source generator if so. Evaluating our approach on two multi-source datasets, we obtain 97.17% and 94.03% for video source detection. We compare against the prior deepfake source detector and other complex architectures. We also analyze the importance of magnification amount, phase extraction window, backbone network architecture, sample counts, and sample lengths. Finally, we report our results for different skin tones to assess the bias.