Detecting Deepfake by Creating Spatio-Temporal Regularity Disruption
This work addresses the problem of limited generalization in deepfake detection for security and media verification, offering an incremental improvement by leveraging pseudo-fake videos.
The paper tackles the challenge of generalizing deepfake detection to unseen forgery types by proposing a method that distinguishes 'regularity disruption' in fake videos, achieving excellent performance on several datasets without using fake videos during training.
Despite encouraging progress in deepfake detection, generalization to unseen forgery types remains a significant challenge due to the limited forgery clues explored during training. In contrast, we notice a common phenomenon in deepfake: fake video creation inevitably disrupts the statistical regularity in original videos. Inspired by this observation, we propose to boost the generalization of deepfake detection by distinguishing the "regularity disruption" that does not appear in real videos. Specifically, by carefully examining the spatial and temporal properties, we propose to disrupt a real video through a Pseudo-fake Generator and create a wide range of pseudo-fake videos for training. Such practice allows us to achieve deepfake detection without using fake videos and improves the generalization ability in a simple and efficient manner. To jointly capture the spatial and temporal disruptions, we propose a Spatio-Temporal Enhancement block to learn the regularity disruption across space and time on our self-created videos. Through comprehensive experiments, our method exhibits excellent performance on several datasets.