Root exploit detection and features optimization: Mobile device and blockchain based medical data management

Ahmad Firdaus, Zainal Abidin and Nor Badrul, Anuar and Mohd Faizal, Ab Razak and Targio Hashem, Ibrahim Abaker and Syafiq, Bachok and Sangaiah, Arun Kumar (2018) Root exploit detection and features optimization: Mobile device and blockchain based medical data management. Journal of Medical Systems, 42 (6). pp. 1-23. ISSN 0148-5598. (Published)

[img]
Preview
Pdf
Root exploit detection and features optimization- Mobile device and blockchain based medical data management.pdf

Download (274kB) | Preview

Abstract

The increasing demand for Android mobile devices and blockchain has motivated malware creators to develop mobile malware to compromise the blockchain. Although the blockchain is secure, attackers have managed to gain access into the blockchain as legal users, thereby comprising important and crucial information. Examples of mobile malware include root exploit, botnets, and Trojans and root exploit is one of the most dangerous malware. It compromises the operating system kernel in order to gain root privileges which are then used by attackers to bypass the security mechanisms, to gain complete control of the operating system, to install other possible types of malware to the devices, and finally, to steal victims’ private keys linked to the blockchain. For the purpose of maximizing the security of the blockchain-based medical data management (BMDM), it is crucial to investigate the novel features and approaches contained in root exploit malware. This study proposes to use the bio-inspired method of practical swarm optimization (PSO) which automatically select the exclusive features that contain the novel android debug bridge (ADB). This study also adopts boosting (adaboost, realadaboost, logitboost, and multiboost) to enhance the machine learning prediction that detects unknown root exploit, and scrutinized three categories of features including (1) system command, (2) directory path and (3) code-based. The evaluation gathered from this study suggests a marked accuracy value of 93% with Logitboost in the simulation. Logitboost also helped to predicted all the root exploit samples in our developed system, the root exploit detection system (RODS).

Item Type: Article
Uncontrolled Keywords: Blockchain; Root exploit; Static analysis; Android; Machine learning
Subjects: Q Science > QA Mathematics > QA76 Computer software
Faculty/Division: Faculty of Computer System And Software Engineering
Depositing User: Mrs. Neng Sury Sulaiman
Date Deposited: 03 Dec 2018 08:43
Last Modified: 03 Dec 2018 08:43
URI: http://umpir.ump.edu.my/id/eprint/23001
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item