Generative Model-Based Attack on Learnable Image Encryption for Privacy-Preserving Deep Learning. (arXiv:2303.05036v1 [cs.CV])

In this paper, we propose a novel generative model-based attack on learnable
image encryption methods proposed for privacy-preserving deep learning. Various
learnable encryption methods have been studied to protect the sensitive visual
information of plain images, and some of them have been investigated to be
robust enough against all existing attacks. However, previous attacks on image
encryption focus only on traditional cryptanalytic attacks or reverse
translation models, so these attacks cannot recover any visual information if a
block-scrambling encryption step, …

attack attacks cryptanalytic attacks deep learning encryption focus generative images information novel privacy protect reverse