arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.11295cs.CV
收藏

SimuFreeMark:一种无需噪声模拟的抗图像编辑鲁棒水印

SimuFreeMark: A Noise-Simulation-Free Robust Watermarking Against Image Editing

College of Computer Science and Artificial Intelligence, Fudan University(计算机科学与人工智能学院,复旦大学)

Yichao Tang, Mingyang Li, Di Miao, Sheng Li, Zhenxing Qian, Xinpeng Zhang

AI总结:

针对AIGC发展下鲁棒图像水印需抵御传统与语义攻击的需求,提出无需噪声模拟的SimuFreeMark框架,利用图像低频成分稳定性嵌入水印并结合预训练VAE,实验证明其攻击抵御能力及视觉质量均优于现有方法。

摘要:

人工智能生成内容(AIGC)的发展使得对鲁棒图像水印的需求愈发迫切,这类水印需同时抵御传统信号处理与新型语义编辑攻击。当前基于深度学习的方法依赖含手工噪声模拟层的训练,这本质上限制了它们对未知失真的泛化能力。本文提出SimuFreeMark——一种无需噪声模拟的水印框架,通过利用图像低频成分的固有稳定性来规避该限制。我们首先系统地证实,低频成分对多种攻击具有显著鲁棒性;在此基础上,SimuFreeMark直接将水印嵌入低频成分的深度特征空间,并利用预训练变分自动编码器(VAE)将水印与结构稳定的图像表示绑定,该设计完全消除了训练期间对噪声模拟的需求。大量实验表明,SimuFreeMark在多种传统及语义攻击下均优于现有方法,同时保持了卓越的视觉质量。

英文摘要:

The advancement of artificial intelligence generated content (AIGC) has created a pressing need for robust image watermarking that can withstand both conventional signal processing and novel semantic editing attacks. Current deep learning-based methods rely on training with hand-crafted noise simulation layers, which inherently limit their generalization to unforeseen distortions. In this work, we propose $\textbf{SimuFreeMark}$, a noise-$\underline{\text{simu}}$lation-$\underline{\text{free}}$ water$\underline{\text{mark}}$ing framework that circumvents this limitation by exploiting the inherent stability of image low-frequency components. We first systematically establish that low-frequency components exhibit significant robustness against a wide range of attacks. Building on this foundation, SimuFreeMark embeds watermarks directly into the deep feature space of the low-frequency components, leveraging a pre-trained variational autoencoder (VAE) to bind the watermark with structurally stable image representations. This design completely eliminates the need for noise simulation during training. Extensive experiments demonstrate that SimuFreeMark outperforms state-of-the-art methods across a wide range of conventional and semantic attacks, while maintaining superior visual quality.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑