An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applications

TL;DR

This paper reviews image transformation techniques with secret keys that enable image protection, feature embedding, and compatibility with machine learning, focusing on learnable encryption for privacy and robustness.

Contribution

It provides a comprehensive overview of learnable image encryption methods, their algorithms, performance, and robustness against attacks, highlighting their applications in privacy-preserving machine learning.

Findings

Transformations enable image protection and feature embedding.

Encrypted images can be compressed and learned by machine learning models.

The methods demonstrate robustness against various attack types.

Abstract

This article presents an overview of image transformation with a secret key and its applications. Image transformation with a secret key enables us not only to protect visual information on plain images but also to embed unique features controlled with a key into images. In addition, numerous encryption methods can generate encrypted images that are compressible and learnable for machine learning. Various applications of such transformation have been developed by using these properties. In this paper, we focus on a class of image transformation referred to as learnable image encryption, which is applicable to privacy-preserving machine learning and adversarially robust defense. Detailed descriptions of both transformation algorithms and performances are provided. Moreover, we discuss robustness against various attacks.