Luminark: Training-free, Probabilistically-Certified Watermarking for General Vision Generative Models

📝 Original Info

• Title: Luminark: Training-free, Probabilistically-Certified Watermarking for General Vision Generative Models
• ArXiv ID: 2601.01085
• Date: 2026-01-03
• Authors: Jiayi Xu, Zhang Zhang, Yuanrui Zhang, Ruitao Chen, Yixian Xu, Tianyu He, Di He

📝 Abstract

In this paper, we introduce Luminark, a trainingfree 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 patchlevel 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 watermark guidance. This design enables Luminark to achieve generality across stateof-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 demo...

📄 Full Content

...(본문 내용이 길어 생략되었습니다. 사이트에서 전문을 확인해 주세요.)