Guidance Watermarking for Diffusion Models
This addresses the need for robust watermarking in AI-generated content, offering a complementary technique to existing methods, though it is incremental as it builds on prior watermarking schemes.
The paper tackles the problem of watermarking diffusion models by introducing a method that guides the diffusion process using gradients from any off-the-shelf watermark decoder, effectively converting post-hoc schemes into in-generation embedding without retraining. The result shows that this approach preserves image quality and diversity while being robust to attacks, as validated on various models and detectors.
This paper introduces a novel watermarking method for diffusion models. It is based on guiding the diffusion process using the gradient computed from any off-the-shelf watermark decoder. The gradient computation encompasses different image augmentations, increasing robustness to attacks against which the decoder was not originally robust, without retraining or fine-tuning. Our method effectively convert any \textit{post-hoc} watermarking scheme into an in-generation embedding along the diffusion process. We show that this approach is complementary to watermarking techniques modifying the variational autoencoder at the end of the diffusion process. We validate the methods on different diffusion models and detectors. The watermarking guidance does not significantly alter the generated image for a given seed and prompt, preserving both the diversity and quality of generation.