On the Coexistence and Ensembling of Watermarks

2025/01/29 by Aleksandar Petrov, Petrov, Aleksandar, Shruti Agarwal +7 · 1 citation
Social Sciences · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Computers and Society (cs.CY) #FOS: Computer and information sciences #Historical Geography and Cartography

paper · pdf · doi:10.48550/arxiv.2501.17356

openalex publication_date 2025/01/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• We Can Hide More Bits: The Unused Watermarking Capacity in Theory and in Practice

Related

• Go Wide or Go Deep: Levering Watermarking Performance with Computational Cost for Specific Images
• We Can Hide More Bits: The Unused Watermarking Capacity in Theory and in Practice
• Robust Watermarks Leak: Channel-Aware Feature Extraction Enables Adversarial Watermark Manipulation
• Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances
• Picking watermarks from noise (PWFN): an improved robust watermarking model against intensive distortions