Security Evaluation of Compressible Image Encryption for Privacy-Preserving Image Classification against Ciphertext-only Attacks

TL;DR

This paper evaluates the security of block scrambling image encryption, used in privacy-preserving image classification, against ciphertext-only attacks, especially focusing on scenarios with a small number of encrypted blocks.

Contribution

It provides an analysis of the security of block scrambling encryption against jigsaw puzzle solver attacks for small block numbers, filling a gap in existing research.

Findings

Security degrades with fewer encrypted blocks.

Jigsaw puzzle solver attacks are effective against small block encryption.

The study highlights limitations of current encryption schemes in low-block scenarios.

Abstract

The security of learnable image encryption schemes for image classification using deep neural networks against several attacks has been discussed. On the other hand, block scrambling image encryption using the vision transformer has been proposed, which applies to lossless compression methods such as JPEG standard by dividing an image into permuted blocks. Although robustness of the block scrambling image encryption against jigsaw puzzle solver attacks that utilize a correlation among the blocks has been evaluated under the condition of a large number of encrypted blocks, the security of encrypted images with a small number of blocks has never been evaluated. In this paper, the security of the block scrambling image encryption against ciphertext-only attacks is evaluated by using jigsaw puzzle solver attacks.