Robust Watermarking for Diffusion Models: A Unified Multi-Dimensional Recipe

24 Sept 2024 (modified: 15 Nov 2024)ICLR 2025 Conference Withdrawn SubmissionEveryoneRevisionsBibTeXCC BY 4.0
Keywords: Diffusion model, Watermark, Unified framework
Abstract: Diffusion models are known for the supreme capability to generate realistic images. However, ethical concerns, such as copyright protection and generation of inappropriate content, pose significant challenges for the practical deployment of diffusion models. Recent work has proposed a flurry of watermarking techniques that inject visually noteless patterns into generated images, offering a promising solution to these issues. While effective, the essential elements for watermarking and the interconnections among various methods are still chaos. In this paper, we dissect the design principles of state-of-the-art watermarking techniques and introduce a unified framework. We identify a set of dimensions that explain the manipulation enforced by watermarking methods, including the distribution of individual elements, the specification of watermark regions within each channel, and the choice of channels for watermark embedding. Moreover, under this framework we instantiate a new watermarking method to minimize impacts on the model performance from a distributional perspective. Through the empirical studies on regular text-to-image applications and the first systematic attempt on watermarking image-to-image diffusion models, we thoroughly verify the effectiveness of our proposed framework through comprehensive evaluations. On all the diffusion models, including Stable Diffusion, our approach induced from the proposed framework not only preserves image quality but also outperforms existing methods in robustness against a range of attacks.
Supplementary Material: zip
Primary Area: other topics in machine learning (i.e., none of the above)
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.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
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: 3937
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview