Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models

arXiv:2404.04956v1 Announce Type: new
Abstract: Ethical concerns surrounding copyright protection and inappropriate content generation pose challenges for the practical implementation of diffusion models. One effective solution involves watermarking the generated images. However, existing methods often compromise the model performance or require additional training, which is undesirable for operators and users. To address this issue, we propose Gaussian Shading, a diffusion model watermarking technique that is both performance-lossless and training-free, while serving the dual purpose of copyright protection and tracing of …

abstract arxiv challenges concerns content generation copyright copyright protection cs.cr cs.cv diffusion diffusion models ethical generated however image images implementation inappropriate operators performance practical protection solution training type watermarking