利用生成先验对抗图像编辑的鲁棒水印技术：从基准测试到进展

Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances

October 24, 2024

作者: Shilin Lu, Zihan Zhou, Jiayou Lu, Yuanzhi Zhu, Adams Wai-Kin Kong

cs.AI

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支持的先进图像编辑技术的影响。这些模型可以在编辑过程中扭曲嵌入的水印，给版权保护带来重大挑战。在这项工作中，我们介绍了W-Bench，这是第一个旨在评估水印方法对抗各种图像编辑技术的鲁棒性的综合基准。这些技术包括图像再生、全局编辑、局部编辑和图像到视频生成。通过对十一种代表性水印方法针对普遍编辑技术的广泛评估，我们展示了大多数方法在此类编辑后无法检测到水印。为了解决这一局限性，我们提出了VINE，一种水印方法，显著增强了对各种图像编辑技术的鲁棒性，同时保持高图像质量。我们的方法涉及两个关键创新：(1)我们分析了图像编辑的频率特性，并确定模糊失真具有类似的频率特性，这使我们能够在训练过程中将其用作替代攻击，以增强水印的鲁棒性；(2)我们利用大规模预训练的扩散模型SDXL-Turbo，将其调整为水印任务，以实现更不可察觉和更强大的水印嵌入。实验结果表明，我们的方法在各种图像编辑技术下实现了出色的水印性能，在图像质量和鲁棒性方面均优于现有方法。代码可在https://github.com/Shilin-LU/VINE找到。

English

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.