Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.17356 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910803393773568 |
|---|---|
| author | Petrov, Aleksandar Agarwal, Shruti Torr, Philip H. S. Bibi, Adel Collomosse, John |
| author_facet | Petrov, Aleksandar Agarwal, Shruti Torr, Philip H. S. Bibi, Adel Collomosse, John |
| contents | Watermarking, the practice of embedding imperceptible information into media such as images, videos, audio, and text, is essential for intellectual property protection, content provenance and attribution. The growing complexity of digital ecosystems necessitates watermarks for different uses to be embedded in the same media. However, to detect and decode all watermarks, they need to coexist well with one another. We perform the first study of coexistence of deep image watermarking methods and, contrary to intuition, we find that various open-source watermarks can coexist with only minor impacts on image quality and decoding robustness. The coexistence of watermarks also opens the avenue for ensembling watermarking methods. We show how ensembling can increase the overall message capacity and enable new trade-offs between capacity, accuracy, robustness and image quality, without needing to retrain the base models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_17356 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | On the Coexistence and Ensembling of Watermarks Petrov, Aleksandar Agarwal, Shruti Torr, Philip H. S. Bibi, Adel Collomosse, John Computer Vision and Pattern Recognition Artificial Intelligence Computers and Society Watermarking, the practice of embedding imperceptible information into media such as images, videos, audio, and text, is essential for intellectual property protection, content provenance and attribution. The growing complexity of digital ecosystems necessitates watermarks for different uses to be embedded in the same media. However, to detect and decode all watermarks, they need to coexist well with one another. We perform the first study of coexistence of deep image watermarking methods and, contrary to intuition, we find that various open-source watermarks can coexist with only minor impacts on image quality and decoding robustness. The coexistence of watermarks also opens the avenue for ensembling watermarking methods. We show how ensembling can increase the overall message capacity and enable new trade-offs between capacity, accuracy, robustness and image quality, without needing to retrain the base models. |
| title | On the Coexistence and Ensembling of Watermarks |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2501.17356 |