利用生成先驗對抗圖像編輯的強健浮水印：從基準測試到進展

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

目前的影像浮水印方法容易受到大規模文本轉影像模型所啟用的高級影像編輯技術的攻擊。這些模型能夠在編輯過程中扭曲嵌入的水印，對版權保護構成重大挑戰。在本研究中，我們介紹了 W-Bench，這是第一個旨在評估浮水印方法對各種影像編輯技術的穩健性的全面基準。這些技術包括影像再生、全域編輯、局部編輯和影像到視訊生成。通過對十一種具代表性的浮水印方法針對普遍編輯技術的廣泛評估，我們證明大多數方法在此類編輯後無法檢測水印。為解決這一限制，我們提出了 VINE，一種能夠顯著增強對各種影像編輯技術的穩健性並保持高影像質量的浮水印方法。我們的方法包含兩個關鍵創新：(1)我們分析影像編輯的頻率特性，並確定模糊失真展現相似的頻率特性，這使我們能夠在訓練過程中將其用作替代攻擊以增強水印的穩健性；(2)我們利用大規模預訓練擴散模型 SDXL-Turbo，將其調整為浮水印任務，實現更不可察覺和穩健的水印嵌入。實驗結果顯示我們的方法在各種影像編輯技術下實現了優異的浮水印性能，優於現有方法在影像質量和穩健性方面。程式碼可在 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.