AI RESEARCH
LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localization
arXiv CS.CV
•
ArXi:2604.23957v1 Announce Type: new 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.