Robust invisible watermarks are widely used to support copyright protection, content provenance, and accountability by embedding hidden signals designed to survive common post-processing operations. However, diffusion-based image editing introduces a fundamentally different class of transformations: it injects noise and reconstructs images through a powerful generative prior, often altering semantic content while preserving photorealism. In this paper, we provide a unified theoretical and empirical analysis showing that non-adversarial diffusion editing can unintentionally degrade or remove robust watermarks. We model diffusion editing as a stochastic transformation that progressively contracts off-manifold perturbations, causing the low-amplitude signals used by many watermarking schemes to decay. Our analysis derives bounds on watermark signal-to-noise ratio and mutual information along diffusion trajectories, yielding conditions under which reliable recovery becomes information-theoretically impossible. We further evaluate representative watermarking systems under a range of diffusion-based editing scenarios and strengths. The results indicate that even routine semantic edits can significantly reduce watermark recoverability. Finally, we discuss the implications for content provenance and outline principles for designing watermarking approaches that remain robust under generative image editing.

翻译：鲁棒不可见水印通过嵌入能够经受常见后处理操作的隐藏信号，被广泛用于支持版权保护、内容溯源与责任认定。然而，基于扩散的图像编辑引入了一类根本不同的变换：它通过注入噪声并借助强大的生成先验重建图像，通常在保持照片级真实感的同时改变语义内容。本文提供了一个统一的理论与实证分析，表明非对抗性的扩散编辑可能无意中削弱或移除鲁棒水印。我们将扩散编辑建模为一种随机变换，该变换逐步压缩流形外的扰动，导致许多水印方案所使用的低幅度信号衰减。我们的分析推导了沿扩散轨迹的水印信噪比与互信息边界，从而得出了可靠恢复在信息论意义上变得不可能的条件。我们进一步在一系列基于扩散的编辑场景与强度下评估了代表性水印系统。结果表明，即使是常规的语义编辑也可能显著降低水印的可恢复性。最后，我们讨论了这对内容溯源的影响，并概述了设计在生成式图像编辑下仍保持鲁棒性的水印方法的原则。