Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.23957 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914509517488128 |
|---|---|
| author | Zeng, Bokang Gao, Zheng Li, Xiaoyu Feng, Xiaoyan Jiang, Jiaojiao |
| author_facet | Zeng, Bokang Gao, Zheng Li, Xiaoyu Feng, Xiaoyan Jiang, Jiaojiao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_23957 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localization Zeng, Bokang Gao, Zheng Li, Xiaoyu Feng, Xiaoyan Jiang, Jiaojiao Computer Vision and Pattern Recognition 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. |
| title | LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.23957 |