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

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 encryp...

Full description

Saved in:
Bibliographic Details
Published inAPSIPA transactions on signal and information processing Vol. 11; no. 1
Main Authors Kiya, Hitoshi, Maung, April Pyone Maung, Kinoshita, Yuma, Imaizumi, Shoko, Shiota, Sayaka
Format Journal Article
LanguageEnglish
Published Boston — Delft Now Publishers 01.01.2022
Subjects
Engineering
Signal Processing
Technology
Online AccessGet full text

Cover

More Information
Summary: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.
Bibliography:Compressible encryption
privacy-preserving machine learning
adversarial defense
learnable encryption
encryption-then-compression
Now Publishers
model protection
SIP-2021-0048
ISSN:2048-7703
2048-7703
DOI:10.1561/116.00000048