SAT-LDM: Provably Generalizable Image Watermarking for Latent Diffusion Models with Self-Augmented Training
Keywords: image generation, watermarking, latent diffusion model
Abstract: The proliferation of AI-generated images necessitates effective watermarking to protect intellectual property and identify fake content. While existing training-based watermarking methods show promise, they often struggle with generalization across diverse image styles and tend to produce noticeable artifacts. To this end, we introduce a provably generalizable image watermarking method for Latent Diffusion Models with Self-Augmented Training (SAT-LDM), which aligns the training and testing phases by a free generation distribution to bolster the watermarking module’s generalization capabilities. We theoretically consolidate our method by proving that the free generation distribution contributes to its tight generalization bound without the need to collect new data. Extensive experimental results demonstrate that SAT-LDM achieves robust watermarking while significantly improving the quality of watermarked images across diverse styles. Furthermore, we conduct experimental analyses to demonstrate the strong generalization abilities of SAT-LDM. We hope our method offers a practical and convenient solution for securing high-fidelity AI-generated content.
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: 3553
Loading