RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees

arXiv:2403.18774v1 Announce Type: cross
Abstract: Safeguarding intellectual property and preventing potential misuse of AI-generated images are of paramount importance. This paper introduces a robust and agile plug-and-play watermark detection framework, dubbed as RAW. As a departure from traditional encoder-decoder methods, which incorporate fixed binary codes as watermarks within latent representations, our approach introduces learnable watermarks directly into the original image data. Subsequently, we employ a classifier that is jointly trained with the watermark to detect the presence of the watermark. …

abstract agile ai-generated images arxiv binary cs.cr cs.cv cs.lg decoder detection encoder encoder-decoder framework generated images importance intellectual property misuse paper property raw robust type watermark