Saved in:
Bibliographic Details
Main Authors: Petrov, Aleksandar, Agarwal, Shruti, Torr, Philip H. S., Bibi, Adel, Collomosse, John
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