Efficient Neuroimaging Data Security and Encryption Using Pixel-Based Homomorphic Residue Number System

作     者：Usman, Lateef Opeyemi Muniyandi, Ravie Chandren Usman, Morufat Adebola 

作者机构：Research Centre for Cyber Security Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Selangor UKM Bangi 43600 Malaysia Department of Computer Science Tai Solarin University of Education P.M.B. 2118 Ogun State Ijagun Ijebu-Ode Nigeria 

出 版 物：《SN Computer Science》 (SN COMPUT. SCI.)

年 卷 期：2023年第4卷第6期

页      面：834页

基　　金：Ministry of Higher Education, Malaysia, MOHE, (FRGS/1/2021/ICT07/UKM/02/1) Ministry of Higher Education, Malaysia, MOHE Universiti Kebangsaan Malaysia, UKM 

主　　题：Cipher images Homomorphic encryption Neural biomarkers Neuroimages Residue number system 

摘      要：In recent times, there has been an increasing attention in designing a homomorphic privacy-preserving classification method for neuro-images based on the residue number system (RNS) and deep CNN models. This article presents the RNS homomorphic encryption system for neuro-images and evaluates its security efficiency with respect to moduli set { 2 n- 1 , 2 n, 2 n+1- 1 } . The efficiency of the proposed system is evaluated through the application of three metrics, namely visual inspection, encoding analysis, and security analysis. The analysis demonstrates that the proposed RNS scheme is a fully homomorphic encryption (FHE) scheme that can encrypt and decrypt neuroimages without compromising any essential neural biomarker features. Additionally, the scheme is robust against statistical attacks like histogram, brute force, correlation coefficient, and key sensitivity. Thus, the proposed RNS-FHE scheme can be utilized for any neuroimaging dataset and is appropriate for the design of homomorphic privacy-preserving methods when compared to the current state-of-the-art. In summary, the contribution and novelty of this study is the development of a systematic RNS-FHE privacy-preserving approach for efficient neuroimaging dataset homomorphic encryption. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.