An Undetectable Watermark for Generative Image Models
Keywords: Watermarking, AI Safety, Diffusion Models, Generative AI
TL;DR: We present a robust image watermarking scheme that is provably quality-preserving, and demonstrate that all prior schemes degrade quality.
Abstract: We present the first undetectable watermarking scheme for generative image models.
_Undetectability_ ensures that no efficient adversary can distinguish between watermarked and un-watermarked images, even after making many adaptive queries.
In particular, an undetectable watermark does not degrade image quality under any efficiently computable metric.
Our scheme works by selecting the initial latents of a diffusion model using a pseudorandom error-correcting code (Christ and Gunn, 2024), a strategy which guarantees undetectability and robustness. We experimentally demonstrate that our watermarks are quality-preserving and robust using Stable Diffusion 2.1.
Our experiments verify that, in contrast to _every prior scheme_ we tested, our watermark does not degrade image quality.
Our experiments also demonstrate robustness: existing watermark removal attacks fail to remove our watermark from images without significantly degrading the quality of the images.
Finally, we find that we can robustly encode 512 bits in our watermark, and up to 2500 bits when the images are not subjected to watermark removal attacks.
Our code is available at https://github.com/XuandongZhao/PRC-Watermark.
Primary Area: alignment, fairness, safety, privacy, and societal considerations
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 11846
Loading