Forgery-aware Layer Masking and Multi-Artifact Subspace Decomposition for Generalizable Deepfake Detection

ArXi:2601.01041v2 Announce Type: replace Deepfake detection remains highly challenging, particularly in cross-dataset scenarios and complex real-world settings. This challenge mainly arises because artifact patterns vary substantially across different forgery methods, whereas adapting pretrained models to such artifacts often overemphasizes forgery-specific cues and disturbs semantic representations, thereby weakening generalization. Existing approaches typically rely on full-parameter fine-tuning or auxiliary supervision to improve discrimination.