Divide and Conquer: Reliable Multi-View Evidential Learning for Deepfake Detection

ArXi:2606.01885v1 Announce Type: new With the evolution of generative models, deepfakes have achieved near-perfect semantic realism, leaving forensic traces only in subtle structural anomalies. However, existing single-view paradigms often fail to generalize, as dominant semantic features overwhelm subtle artifact cues within entangled representations. This imbalance leads to overconfident yet brittle predictions -- a phenomenon we term the Semantic Masking Effect.