On the Coexistence and Ensembling of Watermarks

TL;DR

This paper investigates how multiple deep image watermarks can coexist in the same media with minimal quality loss and explores ensembling techniques to enhance watermark capacity and robustness without retraining models.

Contribution

It is the first study on coexistence of deep watermarks and demonstrates how ensembling improves capacity and robustness without retraining.

Findings

Open-source watermarks can coexist with minor impact on quality.

Ensembling increases message capacity and robustness.

No retraining needed for improved performance.

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.