A LATTICE CRYPTOGRAPHY AND FOG COMPUTING-BASED MODEL FOR PRIVACY PRESERVATION OF MEDICAL BIG DATA

Abstract

The expanding success of cloud computing in the management of Electronic Health Records (EHRs) also comes with loads of challenges, especially those that bothers on the preservation of users’ privacy, personal data integrity, and even reduction in computational resource demand. Today, there is explosive growth in concerns for security of data exchanged between edge node devices (users) and the cloud server. Almost all the existing proposed methods for overcoming these privacy issues have significant shortcomings such as, ineffectiveness or inefficiencies, as well as their lack of the lightweight property required by resource constrained devices used by users at the edge of the network. This current research work is therefore motivated to develop a lattice cryptography-based quantum attack-resistant security system for preserving privacy and ensuring data integrity in health cloud big data. The lattice encryption algorithm is used to encrypt medical records or data before uploading them on to the storage servers. For every file uploaded to the cloud server, a decoy (or fake equivalent) file is generated and stored in the decoy medical files repository that resides on a decoy server (in the fog facility). This honeypot security paradigm is used here for deceiving/luring potential attackers (unauthorized), to leaving trails behind each time they make attempt to access secured medical records. This chemistry adds multiple layers of security and satisfy requirements such as capacity, security and robustness for secure medical data transmission in a fog-cloud computing environment. The proposed health cloud data security solution was implemented using PHP/Python programming language, on a Windows 10 Operating System running on a PC characterized by 8GB of RAM, 2TB of Hard Disk, Intel Core i7. Comparative evaluation of the proposed solution was then carried out using standard metrics such as time consumption/computation time, throughput, memory requirement, and bandwidth consumption. Results obtained reveals that the developed system performed better than existing ones in terms of having robustness, requiring far lesser computation time, and the lightweight property