An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applications
This is an incremental overview article summarizing existing methods for image transformation with a secret key, addressing privacy and security issues in machine learning applications.
The paper provides an overview of learnable image encryption methods that protect visual information and embed key-controlled features, focusing on applications in privacy-preserving machine learning and adversarially robust defense, with detailed descriptions of algorithms and performance.
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.