WaterFlow: Learning Fast & Robust Watermarks using Stable Diffusion
This addresses the need for fast and robust watermarking in computer vision, particularly for generated images, though it appears incremental as it builds on existing latent diffusion models.
The paper tackled the problem of embedding watermarks in images, which is critical due to the rise of generated imagery, by proposing WaterFlow, a method that achieves state-of-the-art robustness and is the first to defend against difficult combination attacks, with validation on datasets like MS-COCO, DiffusionDB, and WikiArt.
The ability to embed watermarks in images is a fundamental problem of interest for computer vision, and is exacerbated by the rapid rise of generated imagery in recent times. Current state-of-the-art techniques suffer from computational and statistical challenges such as the slow execution speed for practical deployments. In addition, other works trade off fast watermarking speeds but suffer greatly in their robustness or perceptual quality. In this work, we propose WaterFlow (WF), a fast and extremely robust approach for high fidelity visual watermarking based on a learned latent-dependent watermark. Our approach utilizes a pretrained latent diffusion model to encode an arbitrary image into a latent space and produces a learned watermark that is then planted into the Fourier Domain of the latent. The transformation is specified via invertible flow layers that enhance the expressivity of the latent space of the pre-trained model to better preserve image quality while permitting robust and tractable detection. Most notably, WaterFlow demonstrates state-of-the-art performance on general robustness and is the first method capable of effectively defending against difficult combination attacks. We validate our findings on three widely used real and generated datasets: MS-COCO, DiffusionDB, and WikiArt.