Shallow Diffuse: Robust and Invisible Watermarking through Low-Dim Subspaces in Diffusion Models

Watermarking is a crucial technique for identifying these AI-generated images and preventing their misuse. In this paper, we introduce, a new watermarking technique that embeds robust and invisible watermarks into diffusion model outputs. Unlike existing approaches that integrate watermarking throughout the entire diffusion sampling process, decouples these steps by leveraging the presence of a low-dimensional subspace in the image generation process. This method ensures that a substantial portion of the watermark lies in the null space of this subspace, effectively separating it from the image generation process. Our theoretical and empirical analyses show that this decoupling strategy greatly enhances the consistency of data generation and the detectability of the watermark. Extensive experiments further validate that outperforms existing watermarking methods in terms of consistency.