Generalized Deepfakes Detection with Reconstructed-Blended Images and Multi-scale Feature Reconstruction Network

The growing diversity of digital face manipulation techniques has led to an urgent need for a universal and robust detection technology to mitigate the risks posed by malicious forgeries. We present a blended-based detection approach that has robust applicability to unseen datasets, seamlessly integrating two key components: a method for generating synthetic training samples, specifically Reconstructed Blended Images, which incorporates potential deepfake generator artifacts; and a detection model for multi-scale feature reconstruction, which is adept at capturing generic boundary artifacts and noise distribution anomalies induced by digital face manipulations. Empirical results demonstrate that this approach results in better performance in both cross-manipulation detection and cross-dataset detection on unseen data.