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

Bokang Zeng, Zheng Gao, Xiaoyu Li, Xiaoyan Feng, Jiaojiao Jiang

ACM International Conference on Multimedia (MM), 2026

PDF arXiv

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.

BibTeX

@inproceedings{gao2026lava,
  title     = {LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localization},
  author    = {Zeng, Bokang and Gao, Zheng and Li, Xiaoyu and Feng, Xiaoyan and Jiang, Jiaojiao},
  booktitle = {ACM International Conference on Multimedia (MM)},
  year      = {2026},
}