On the Coexistence and Ensembling of Watermarks
This addresses the need for multiple watermarks in digital ecosystems for content protection, but it is incremental as it builds on existing watermarking methods.
The study tackled the problem of embedding multiple watermarks in the same image for intellectual property protection, finding that various open-source watermarks can coexist with only minor impacts on image quality and decoding robustness, and that ensembling these methods increases message capacity and enables new trade-offs without retraining.
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.