arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.12688cs.CR
收藏

Robust-Wide:针对指令驱动图像编辑的鲁棒水印

Robust-Wide: Robust Watermarking against Instruction-driven Image Editing

Runyi Hu, Jie Zhang, Ting Xu, Jiwei Li, Tianwei Zhang

AI总结:

针对指令驱动图像编辑,提出首个鲁棒水印方法Robust-Wide,通过PIDSG模块嵌入语义感知水印,实现低误码率提取且不影响图像质量。

摘要:

指令驱动图像编辑允许用户在一次前向传播中根据文本指令快速编辑图像。然而,恶意用户很容易利用该技术制造虚假图像,这可能导致信任危机并损害原始图像所有者的权益。水印是追踪此类恶意行为的常见解决方案。不幸的是,指令驱动图像编辑能够在语义层面显著改变含水印图像,使得当前最先进的水印方法失效。为解决这一问题,我们提出了Robust-Wide,这是首个针对指令驱动图像编辑的鲁棒水印方法。具体而言,我们遵循深度鲁棒水印的经典结构,包括编码器、噪声层和解码器。为了实现针对语义失真的鲁棒性,我们引入了一种新颖的部分指令驱动去噪采样引导(PIDSG)模块,该模块包含多种指令注入以及在不同语义级别对图像的大量修改。借助PIDSG,编码器倾向于将水印嵌入到更鲁棒且语义感知的区域,这些区域即使在严重图像编辑后仍然存在。实验表明,Robust-Wide能够有效地从编辑后的图像中提取水印,对于64位水印消息,其误码率低至约2.6%。同时,它对原始图像的视觉质量和可编辑性仅产生可忽略的影响。此外,Robust-Wide对不同采样配置以及其他流行的图像编辑方法(如ControlNet-InstructPix2Pix、MagicBrush、Inpainting和DDIM Inversion)具有通用鲁棒性。代码和模型可在https://github.com/hurunyi/Robust-Wide获取。

英文摘要:

Instruction-driven image editing allows users to quickly edit an image according to text instructions in a forward pass. Nevertheless, malicious users can easily exploit this technique to create fake images, which could cause a crisis of trust and harm the rights of the original image owners. Watermarking is a common solution to trace such malicious behavior. Unfortunately, instruction-driven image editing can significantly change the watermarked image at the semantic level, making current state-of-the-art watermarking methods ineffective. To remedy it, we propose Robust-Wide, the first robust watermarking methodology against instruction-driven image editing. Specifically, we follow the classic structure of deep robust watermarking, consisting of the encoder, noise layer, and decoder. To achieve robustness against semantic distortions, we introduce a novel Partial Instruction-driven Denoising Sampling Guidance (PIDSG) module, which consists of a large variety of instruction injections and substantial modifications of images at different semantic levels. With PIDSG, the encoder tends to embed the watermark into more robust and semantic-aware areas, which remains in existence even after severe image editing. Experiments demonstrate that Robust-Wide can effectively extract the watermark from the edited image with a low bit error rate of nearly 2.6% for 64-bit watermark messages. Meanwhile, it only induces a neglectable influence on the visual quality and editability of the original images. Moreover, Robust-Wide holds general robustness against different sampling configurations and other popular image editing methods such as ControlNet-InstructPix2Pix, MagicBrush, Inpainting, and DDIM Inversion. Codes and models are available at https://github.com/hurunyi/Robust-Wide.

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。

↑