GaussMarker: Robust Dual-Domain Watermark for Diffusion Models
This addresses copyright protection for diffusion model users, offering a robust solution against image manipulations and advanced attacks, though it is incremental as it builds on existing watermarking methods.
The paper tackles the problem of copyright and misuse in diffusion models by proposing a dual-domain watermarking approach that embeds watermarks in both spatial and frequency domains, achieving state-of-the-art robustness with better recall and lower false positive rates under various distortions and attacks.
As Diffusion Models (DM) generate increasingly realistic images, related issues such as copyright and misuse have become a growing concern. Watermarking is one of the promising solutions. Existing methods inject the watermark into the single-domain of initial Gaussian noise for generation, which suffers from unsatisfactory robustness. This paper presents the first dual-domain DM watermarking approach using a pipelined injector to consistently embed watermarks in both the spatial and frequency domains. To further boost robustness against certain image manipulations and advanced attacks, we introduce a model-independent learnable Gaussian Noise Restorer (GNR) to refine Gaussian noise extracted from manipulated images and enhance detection robustness by integrating the detection scores of both watermarks. GaussMarker efficiently achieves state-of-the-art performance under eight image distortions and four advanced attacks across three versions of Stable Diffusion with better recall and lower false positive rates, as preferred in real applications.