FSBI: Deepfake detection with frequency enhanced self-blended images

Ahmed Abul Hasanaath, Hamzah Luqman, Raed Katib, Saeed Anwar

Abstract: Highlights•Proposing an innovative approach for deepfake detection.•Discussing the efficiency of frequency-based transforms for detecting artifacts on deepfake images.•Evaluating the generalization of the proposed approach by performing cross-dataset evaluation.•Reporting a new state-of-the-art performance in the Celeb-DF dataset.