Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.01085 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911352460673024 |
|---|---|
| author | Xu, Jiayi Zhang, Zhang Zhang, Yuanrui Chen, Ruitao Xu, Yixian He, Tianyu He, Di |
| author_facet | Xu, Jiayi Zhang, Zhang Zhang, Yuanrui Chen, Ruitao Xu, Yixian He, Tianyu He, Di |
| contents | In this paper, we introduce \emph{Luminark}, a training-free and probabilistically-certified watermarking method for general vision generative models. Our approach is built upon a novel watermark definition that leverages patch-level luminance statistics. Specifically, the service provider predefines a binary pattern together with corresponding patch-level thresholds. To detect a watermark in a given image, we evaluate whether the luminance of each patch surpasses its threshold and then verify whether the resulting binary pattern aligns with the target one. A simple statistical analysis demonstrates that the false positive rate of the proposed method can be effectively controlled, thereby ensuring certified detection. To enable seamless watermark injection across different paradigms, we leverage the widely adopted guidance technique as a plug-and-play mechanism and develop the \emph{watermark guidance}. This design enables Luminark to achieve generality across state-of-the-art generative models without compromising image quality. Empirically, we evaluate our approach on nine models spanning diffusion, autoregressive, and hybrid frameworks. Across all evaluations, Luminark consistently demonstrates high detection accuracy, strong robustness against common image transformations, and good performance on visual quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_01085 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Luminark: Training-free, Probabilistically-Certified Watermarking for General Vision Generative Models Xu, Jiayi Zhang, Zhang Zhang, Yuanrui Chen, Ruitao Xu, Yixian He, Tianyu He, Di Computer Vision and Pattern Recognition Artificial Intelligence In this paper, we introduce \emph{Luminark}, a training-free and probabilistically-certified watermarking method for general vision generative models. Our approach is built upon a novel watermark definition that leverages patch-level luminance statistics. Specifically, the service provider predefines a binary pattern together with corresponding patch-level thresholds. To detect a watermark in a given image, we evaluate whether the luminance of each patch surpasses its threshold and then verify whether the resulting binary pattern aligns with the target one. A simple statistical analysis demonstrates that the false positive rate of the proposed method can be effectively controlled, thereby ensuring certified detection. To enable seamless watermark injection across different paradigms, we leverage the widely adopted guidance technique as a plug-and-play mechanism and develop the \emph{watermark guidance}. This design enables Luminark to achieve generality across state-of-the-art generative models without compromising image quality. Empirically, we evaluate our approach on nine models spanning diffusion, autoregressive, and hybrid frameworks. Across all evaluations, Luminark consistently demonstrates high detection accuracy, strong robustness against common image transformations, and good performance on visual quality. |
| title | Luminark: Training-free, Probabilistically-Certified Watermarking for General Vision Generative Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2601.01085 |