利用生成先理实现抗图像编辑的鲁棒水印：从基准评测到方法进展
Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances
AI总结：
本文构建涵盖多类图像编辑的 W-Bench 水印鲁棒性基准，并提出基于模糊替代攻击与 SDXL-Turbo 适配的 VINE 水印方法，在图像质量和抗编辑鲁棒性上优于现有方法。
摘要：
当前的图像水印方法容易受到大规模文本到图像模型所支持的先进图像编辑技术的影响。这些模型会在编辑过程中扭曲已嵌入的水印，从而给版权保护带来重大挑战。在本工作中，我们推出 W-Bench，这是首个综合性基准，旨在评估水印方法针对广泛图像编辑技术的鲁棒性，涵盖图像再生、全局编辑、局部编辑以及图像到视频生成。通过对11种具有代表性的水印方法在主流编辑技术下进行广泛评估，我们证明大多数方法在此类编辑后都无法检测到水印。为解决这一局限，我们提出 VINE，这是一种水印方法，可显著增强针对各类图像编辑技术的鲁棒性，同时保持较高图像质量。我们的方法包含两项关键创新：（1）我们分析图像编辑的频率特征，发现模糊失真具有相似的频率属性，这使我们能够在训练期间将其用作替代攻击，以增强水印鲁棒性；（2）我们利用大规模预训练扩散模型 SDXL-Turbo，将其适配到水印任务中，以实现更不易察觉且更鲁棒的水印嵌入。实验结果表明，我们的方法在各种图像编辑技术下均取得出色的水印性能，并在图像质量和鲁棒性方面优于现有方法。代码可在 https://github.com/Shilin-LU/VINE 获取。
英文摘要：
Current image watermarking methods are vulnerable to advanced image editing techniques enabled by large-scale text-to-image models. These models can distort embedded watermarks during editing, posing significant challenges to copyright protection. In this work, we introduce W-Bench, the first comprehensive benchmark designed to evaluate the robustness of watermarking methods against a wide range of image editing techniques, including image regeneration, global editing, local editing, and image-to-video generation. Through extensive evaluations of eleven representative watermarking methods against prevalent editing techniques, we demonstrate that most methods fail to detect watermarks after such edits. To address this limitation, we propose VINE, a watermarking method that significantly enhances robustness against various image editing techniques while maintaining high image quality. Our approach involves two key innovations: (1) we analyze the frequency characteristics of image editing and identify that blurring distortions exhibit similar frequency properties, which allows us to use them as surrogate attacks during training to bolster watermark robustness; (2) we leverage a large-scale pretrained diffusion model SDXL-Turbo, adapting it for the watermarking task to achieve more imperceptible and robust watermark embedding. Experimental results show that our method achieves outstanding watermarking performance under various image editing techniques, outperforming existing methods in both image quality and robustness. Code is available at https://github.com/Shilin-LU/VINE.
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。
