Image Watermarking of Generative Diffusion Models

TL;DR

This paper introduces a novel watermarking technique for diffusion models that embeds versatile, imperceptible watermarks directly into generated images, enabling accurate detection and model differentiation.

Contribution

It proposes an end-to-end training method for embedding and extracting watermarks within diffusion models, improving robustness and versatility over existing frequency domain approaches.

Findings

High accuracy in watermark embedding and detection

Ability to distinguish between different watermarks

Watermarks remain imperceptible in generated images

Abstract

Embedding watermarks into the output of generative models is essential for establishing copyright and verifiable ownership over the generated content. Emerging diffusion model watermarking methods either embed watermarks in the frequency domain or offer limited versatility of the watermark patterns in the image space, which allows simplistic detection and removal of the watermarks from the generated content. To address this issue, we propose a watermarking technique that embeds watermark features into the diffusion model itself. Our technique enables training of a paired watermark extractor for a generative model that is learned through an end-to-end process. The extractor forces the generator, during training, to effectively embed versatile, imperceptible watermarks in the generated content while simultaneously ensuring their precise recovery. We demonstrate highly accurate watermark embedding/detection and show that it is also possible to distinguish between different watermarks embedded with our method to differentiate between generative models.