Research
Physics-Aware Deepfake Detection via Distance-Speech Consistency
arXiv:2610.18485v1 Announce Type: new Abstract: Recent progress in generative models has made talking-head deepfakes highly realistic and easy to create, jeopardizing public trust. However, most audio
arXiv:2610.18485v1 Announce Type: new Abstract: Recent progress in generative models has made talking-head deepfakes highly realistic and easy to create, jeopardizing public trust. However, most audio-visual deepfake detectors rely on lip-speech synchronization and are designed for static, frontal videos, limiting their reliability in dynamic, in-the-wild recordings where the speaker moves and lip cues are degraded or missing. As an alternative, we propose a physics-aware detector for dynamic speaking videos that leverages an acoustic constraint: in real recordings, speech energy varies predictably with speaker-to-camera distance, whereas deepfake generation can break this coupling. Our method combines distance estimates from video with distance-dependent acoustic measures from speech to detect deepfakes. Experiments on in-the-wild benchmarks show that the proposed physical cue is effective in dynamic scenarios, and that it complements lip-sync-based detectors, with a simple ensemble achieving consistent gains across datasets. Codes are available at https://byulharang.github.io/PADD/.
Related
- Ariadne's Thread of LipSync: Unraveling Forgeries via Inconsistency between Lip Motions and Head Poses
- Are DeepFakes Realistic Enough? Exploring Semantic Mismatch as a Novel Challenge
- Only Train Once: Uncertainty-Aware One-Class Learning for Face Authenticity Detection
- Inconsistency-aware Multimodal Schrodinger Bridge for Deepfake Localization
Source: arXiv cs.CV | 2026-10-14