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 2305.16936cs.CV
收藏

CRoSS:扩散模型实现可控、鲁棒且安全的图像隐写术

CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography

Peking University Shenzhen Graduate School(北京大学深圳研究生院);Peng Cheng Laboratory(鹏城实验室)

Jiwen Yu, Xuanyu Zhang, Youmin Xu, Jian Zhang

AI总结:

本文提出CRoSS框架,首次将Stable Diffusion等扩散模型引入图像隐写,利用其免训练图像转换和噪声鲁棒特性,结合LoRAs与ControlNets,在无需额外训练的情况下实现可控、鲁棒且安全的图像隐写。

摘要:

当前的图像隐写技术主要集中在基于载体的方法上,这些方法通常存在泄露秘密图像的风险,并且对退化容器图像的鲁棒性较差。受扩散模型近期发展的启发,我们发现扩散模型的两个特性——无需训练即可实现两幅图像之间的转换,以及对噪声数据的鲁棒性——可用于提升图像隐写任务中的安全性和自然鲁棒性。在扩散模型的选择上,我们选用了Stable Diffusion,一种条件扩散模型,并充分利用开源社区的最新工具,如LoRAs和ControlNets,以提高容器图像的可控性和多样性。总之,我们提出了一种新颖的图像隐写框架,名为可控、鲁棒且安全的图像隐写(CRoSS),与基于载体的图像隐写方法相比,该框架在可控性、鲁棒性和安全性方面具有显著优势。这些优势的获得无需额外训练。据我们所知,这是首次将扩散模型引入图像隐写领域的工作。在实验部分,我们进行了详细的实验,以证明所提出的CRoSS框架在可控性、鲁棒性和安全性方面的优势。

英文摘要:

Current image steganography techniques are mainly focused on cover-based methods, which commonly have the risk of leaking secret images and poor robustness against degraded container images. Inspired by recent developments in diffusion models, we discovered that two properties of diffusion models, the ability to achieve translation between two images without training, and robustness to noisy data, can be used to improve security and natural robustness in image steganography tasks. For the choice of diffusion model, we selected Stable Diffusion, a type of conditional diffusion model, and fully utilized the latest tools from open-source communities, such as LoRAs and ControlNets, to improve the controllability and diversity of container images. In summary, we propose a novel image steganography framework, named Controllable, Robust and Secure Image Steganography (CRoSS), which has significant advantages in controllability, robustness, and security compared to cover-based image steganography methods. These benefits are obtained without additional training. To our knowledge, this is the first work to introduce diffusion models to the field of image steganography. In the experimental section, we conducted detailed experiments to demonstrate the advantages of our proposed CRoSS framework in controllability, robustness, and security.

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。

↑