LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localization
For deepfake detection in short-form videos, LAVA addresses the vulnerability of existing methods to compression and audio-visual asynchrony, offering a more reliable tamper localization solution.
LAVA proposes a calibration-aware audio-visual watermark fusion framework for deepfake tamper detection and localization, achieving near-perfect detection (AP=0.999) and robust performance under compression and multimodal misalignment.
Proactive watermarking offers a promising approach for deepfake tamper detection and localization in short-form videos. However, existing methods often decouple audio and visual evidence and assume that watermark signals remain reliable under real-world degradations, making tamper localization vulnerable to multimodal misalignment and compression distortions. Moreover, existing semi-fragile visual watermarking methods often degrade significantly under codec compression because their embedding bands overlap with compression-sensitive frequency regions. To address these limitations, we propose Layered Audio-Visual Anti-tampering Watermarking (LAVA), a calibration-aware audio-visual watermark fusion framework for deepfake tamper detection and localization. LAVA leverages cross-modal watermark fusion and calibration-aware alignment to preserve consistent and reliable tamper evidence under compression and audio-visual asynchrony, enabling robust tamper localization. Extensive experiments demonstrate that LAVA achieves near-perfect detection performance (AP = 0.999), remains robust to compression and multimodal misalignment, and significantly improves tamper localization reliability over existing audio-visual fusion baselines.