论文标题
针对仅密文的攻击的可学习图像加密方法的视觉安全评估
Visual Security Evaluation of Learnable Image Encryption Methods against Ciphertext-only Attacks
论文作者
论文摘要
已经提出了各种视觉信息保护方法，以保护隐私的深度神经网络（DNNS）。相比之下，已经同时研究了此类保护方法的攻击方法。在本文中，我们根据针对仅密文的攻击（COAS）的视觉安全性（COAS）评估了具有隐私性DNN的最新视觉保护方法。我们专注于蛮力攻击，特征重建攻击（FR-攻击），反变形攻击（ITN-攻击）和基于GAN的攻击（GAN-攻击），这些攻击已提议从视觉保护图像中的普通图像上重建视觉信息。首先总结了各种攻击的细节，然后评估保护方法的视觉安全性。实验结果表明，大多数保护方法，包括像素化的加密，对GAN-攻击没有足够的鲁棒性，而一些保护方法对GAN-攻击足够强大。
Various visual information protection methods have been proposed for privacy-preserving deep neural networks (DNNs). In contrast, attack methods on such protection methods have been studied simultaneously. In this paper, we evaluate state-of-the-art visual protection methods for privacy-preserving DNNs in terms of visual security against ciphertext-only attacks (COAs). We focus on brute-force attack, feature reconstruction attack (FR-Attack), inverse transformation attack (ITN-Attack), and GAN-based attack (GAN-Attack), which have been proposed to reconstruct visual information on plain images from the visually-protected images. The detail of various attack is first summarized, and then visual security of the protection methods is evaluated. Experimental results demonstrate that most of protection methods, including pixel-wise encryption, have not enough robustness against GAN-Attack, while a few protection methods are robust enough against GAN-Attack.
