Several learnable image encryption schemes have been developed for privacy-preserving image classification. This paper focuses on the security block-based image encryption methods that are learnable and JPEG-friendly. Permuting divided blocks in an image is known to enhance robustness against ciphertext-only attacks (COAs), but recently jigsaw puzzle solver attacks have been demonstrated to be able to restore visual information on the encrypted images. In contrast, it has never been confirmed whether encrypted images including noise caused by JPEG-compression are robust. Accordingly, the aim of this paper is to evaluate the security of compressible and learnable encrypted images against jigsaw puzzle solver attacks. In experiments, the security evaluation was carried out on the CIFAR-10 and STL-10 datasets under JPEG-compression.

翻译：多种可学习图像加密方案已被提出用于隐私保护的图像分类。本文聚焦于兼具可学习性与JPEG兼容性的基于块的图像加密方法。已知对图像中的分块进行排列能增强抗唯密文攻击(COAs)的鲁棒性，但近期有研究证明，拼图求解攻击能够恢复加密图像中的视觉信息。然而，目前尚未有研究验证包含JPEG压缩噪声的加密图像是否具有鲁棒性。因此，本文旨在评估可压缩可学习加密图像对抗拼图求解攻击的安全性。实验在CIFAR-10和STL-10数据集上，针对JPEG压缩场景开展了安全性评估。