LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localization

TL;DR

LAVA is a novel layered audio-visual watermarking framework that enhances deepfake tamper detection and localization robustness against compression and misalignment in short videos.

Contribution

It introduces a calibration-aware fusion approach that maintains reliable tamper evidence under real-world degradations, surpassing existing methods.

Findings

Achieves near-perfect detection performance (AP = 0.999)

Remains robust to compression and multimodal misalignment

Improves tamper localization reliability over existing baselines

Abstract

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.