arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.04247cs.CVcs.AI
收藏

使用 Stable Diffusion 的抗攻击图像水印

Attack-Resilient Image Watermarking Using Stable Diffusion

University of Massachusetts(马萨诸塞大学);IBM Watson(IBM沃森研究院);Georgia Institute of Technology(佐治亚理工学院)

Lijun Zhang, Xiao Liu, Antoni Viros Martin, Cindy Xiong Bearfield, Yuriy Brun, Hui Guan

AI总结:

提出 ZoDiac,利用预训练 Stable Diffusion 将水印注入可训练潜空间,在三个基准上实现高检测率、低误报率并抵御强扩散攻击。

摘要:

图像水印对于追踪图像来源和证明所有权至关重要。随着 Stable Diffusion 等能够生成虚假但逼真图像的生成式模型出现,水印对于使人类创作的图像能够被可靠识别变得尤为重要。遗憾的是,同样的 Stable Diffusion 技术也可以去除使用现有方法注入的水印。为解决这一问题,我们提出了 ZoDiac,它利用预训练的 Stable Diffusion 模型将水印注入可训练的潜空间,使水印即使遭受攻击,也能在潜向量中被可靠检测。我们在 MS-COCO、DiffusionDB 和 WikiArt 三个基准上评估 ZoDiac,发现其对最先进的水印攻击具有鲁棒性,水印检测率超过 98%,误报率低于 6.4%,优于最先进的水印方法。我们假设扩散模型中的往复去噪过程在面对强攻击时可能会内在增强水印的鲁棒性,并验证了该假设。研究表明,Stable Diffusion 是实现鲁棒水印的一种有前景的方法,甚至能够抵御基于 Stable Diffusion 的攻击方法。ZoDiac 已开源,可在 https://github.com/zhanglijun95/ZoDiac 获取。

英文摘要:

Watermarking images is critical for tracking image provenance and proving ownership. With the advent of generative models, such as stable diffusion, that can create fake but realistic images, watermarking has become particularly important to make human-created images reliably identifiable. Unfortunately, the very same stable diffusion technology can remove watermarks injected using existing methods. To address this problem, we present ZoDiac, which uses a pre-trained stable diffusion model to inject a watermark into the trainable latent space, resulting in watermarks that can be reliably detected in the latent vector even when attacked. We evaluate ZoDiac on three benchmarks, MS-COCO, DiffusionDB, and WikiArt, and find that ZoDiac is robust against state-of-the-art watermark attacks, with a watermark detection rate above 98% and a false positive rate below 6.4%, outperforming state-of-the-art watermarking methods. We hypothesize that the reciprocating denoising process in diffusion models may inherently enhance the robustness of the watermark when faced with strong attacks and validate the hypothesis. Our research demonstrates that stable diffusion is a promising approach to robust watermarking, able to withstand even stable-diffusion--based attack methods. ZoDiac is open-sourced and available at https://github.com/zhanglijun95/ZoDiac.

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。

↑