Security Evaluation of Compressible and Learnable Image Encryption Against Jigsaw Puzzle Solver Attacks

TL;DR

This paper evaluates the security of JPEG-compression compatible, learnable image encryption methods against jigsaw puzzle solver attacks, focusing on their robustness when images are compressed and contain noise.

Contribution

It provides an empirical security assessment of block-based, learnable image encryption schemes under JPEG compression and noise conditions, which was previously unconfirmed.

Findings

Encrypted images with noise are vulnerable to jigsaw puzzle solver attacks.

JPEG compression impacts the robustness of encrypted images against attacks.

The study highlights the need for improved encryption schemes resilient to such attacks.

Abstract

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.