利用扩散模型净化隐藏信息
Sanitizing Hidden Information with Diffusion Models
AI总结：
本文提出基于扩散模型的DM-SUDS净化方法，用于移除CIFAR-10和ImageNet图像隐写中的隐藏信息，在图像保真指标上显著优于现有深度学习方法，并展示了跨音频领域的通用性。
摘要：
信息隐藏是将数据嵌入另一种数据形式的过程，通常用于掩盖其存在或防止未经授权的访问。该过程常用于各种形式的安全通信（隐写术），可能被恶意行为者用来传播恶意软件、窃取受害者数据以及进行隐蔽通信。近期研究已利用深度神经网络在一种称为净化的防御机制中移除这些隐藏信息。然而，以往的深度学习工作无法在MNIST数据集之外有效扩展。在本工作中，我们提出了一种名为DM-SUDS的新型净化方法，利用扩散模型框架对来自CIFAR-10和ImageNet数据集的图像到图像通用隐写和依赖隐写进行净化/移除隐藏信息。我们使用MSE、PSNR、SSIM和NCC指标将DM-SUDS与三种不同基线进行评估，并通过消融研究提供进一步详细分析。DM-SUDS优于所有三种基线，与以往的深度学习方法相比，图像保真MSE显著改善50.44%，PSNR改善12.69%，SSIM改善11.49%，NCC改善3.26%。此外，我们引入了一种新的评估规范，同时考虑隐藏信息的成功移除（安全性）以及净化后图像的质量（实用性）。我们进一步通过一个音频案例研究应用展示了该方法的通用性，证明其可广泛适用于其他领域。
英文摘要：
Information hiding is the process of embedding data within another form of data, often to conceal its existence or prevent unauthorized access. This process is commonly used in various forms of secure communications (steganography) that can be used by bad actors to propagate malware, exfiltrate victim data, and discreetly communicate. Recent work has utilized deep neural networks to remove this hidden information in a defense mechanism known as sanitization. Previous deep learning works, however, are unable to scale efficiently beyond the MNIST dataset. In this work, we present a novel sanitization method called DM-SUDS that utilizes a diffusion model framework to sanitize/remove hidden information from image-into-image universal and dependent steganography from CIFAR-10 and ImageNet datasets. We evaluate DM-SUDS against three different baselines using MSE, PSNR, SSIM, and NCC metrics and provide further detailed analysis through an ablation study. DM-SUDS outperforms all three baselines and significantly improves image preservation MSE by 50.44%, PSNR by 12.69%, SSIM by 11.49%, and NCC by 3.26% compared to previous deep learning approaches. Additionally, we introduce a novel evaluation specification that considers the successful removal of hidden information (safety) as well as the resulting quality of the sanitized image (utility). We further demonstrate the versatility of this method with an application in an audio case study, demonstrating its broad applicability to additional domains.
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。
