Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection

arXiv:2311.11278v2 Announce Type: replace
Abstract: Deepfake detection faces a critical generalization hurdle, with performance deteriorating when there is a mismatch between the distributions of training and testing data. A broadly received explanation is the tendency of these detectors to be overfitted to forgery-specific artifacts, rather than learning features that are widely applicable across various forgeries. To address this issue, we propose a simple yet effective detector called LSDA (\underline{L}atent \underline{S}pace \underline{D}ata \underline{A}ugmentation), which is based on a heuristic idea: representations …

abstract arxiv augmentation cs.cv data deepfake detection detectors features forgery performance space specificity testing training type