Digital Watermarking

Machine learning (ML) models, especially large pretrained deep learning (DL) models, are of high economic value and must be properly protected with regard to intellectual property rights (IPR). Model watermarking methods are proposed to embed watermarks into the target model, so that, in the event it is stolen, the model’s owner can extract the pre-defined watermarks to assert ownership. Model watermarking methods adopt frequently used techniques like backdoor training, multi-task learning, decision boundary analysis etc. to generate secret conditions that constitute model watermarks or fingerprints only known to model owners. These methods have little or no effect on model performance, which makes them applicable to a wide variety of contexts. In terms of robustness, embedded watermarks must be robustly detectable against varying adversarial attacks that attempt to remove the watermarks. The efficacy of model watermarking methods is showcased in diverse applications including image classification, image generation, image captions, natural language processing and reinforcement learning.

Digital Watermarking for Digital Media discusses the new aspects of digital watermarking in a worldwide context. Approached not only from the technical side, but the business and legal sides as well, this book discusses digital watermarking as it relates to many areas of digital media.

This book constitutes the thoroughly refereed postproceedings of the Second International Workshop on Digital Watermarking, IWDW 2003, held in Seoul, Korea, in October 2004.