WaterFlow: Learning Fast & Robust Watermarks using Stable Diffusion

Vinay Shukla, Prachee Sharma, Ryan A. Rossi, Sungchul Kim, Tong Yu, Aditya Grover

Track: long paper (up to 9 pages)

Keywords: image watermarking, latent diffusion models, computer vision

TL;DR: A new learnable approach for fast and visual watermarking based on latent diffusion models.

Abstract: 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.

Presenter: ~Vinay_Shukla1

Format: Maybe: the presenting author will attend in person, contingent on other factors that still need to be determined (e.g., visa, funding).

Funding: No, the presenting author of this submission does *not* fall under ICLR’s funding aims, or has sufficient alternate funding.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Submission Number: 48