Generalized Deepfakes Detection with Reconstructed-Blended Images and Multi-scale Feature Reconstruction Network
This addresses the need for a universal and robust detection technology to mitigate risks from malicious digital face forgeries, though it appears incremental as it builds on existing detection methods.
The paper tackled the problem of detecting diverse deepfake manipulations by proposing a blended-based detection approach that uses reconstructed blended images for training and a multi-scale feature reconstruction network for capturing artifacts, achieving better performance in cross-manipulation and cross-dataset detection on unseen data.
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. It combines a method for generating synthetic training samples, i.e., reconstructed blended images, that incorporate potential deepfake generator artifacts and a detection model, a multi-scale feature reconstruction network, for capturing the generic boundary artifacts and noise distribution anomalies brought about by digital face manipulations. Experiments demonstrated that this approach results in better performance in both cross-manipulation detection and cross-dataset detection on unseen data.