Root Exploit Detection and Features Optimization: Mobile Device and Blockchain Based Medical Data Management.

Area of Science:

• Cybersecurity
• Mobile Security
• Blockchain Technology

Background:

• Mobile malware, particularly root exploits, poses a significant threat to blockchain security.
• Attackers exploit vulnerabilities to gain unauthorized access, steal private keys, and compromise sensitive data.
• Securing blockchain-based medical data management (BMDM) requires advanced threat detection methods.

Purpose of the Study:

• To investigate novel features of root exploit malware for enhanced detection.
• To develop a robust system for identifying and mitigating mobile malware threats to blockchain systems.
• To improve the security of blockchain-based medical data management.

Main Methods:

• Utilized practical swarm optimization (PSO) for automatic feature selection, focusing on Android Debug Bridge (ADB) related features.
• Employed boosting algorithms (Adaboost, RealAdaboost, Logitboost, MultiBoost) to enhance machine learning prediction accuracy.
• Analyzed system commands, directory paths, and code-based features for root exploit detection.

Main Results:

• Achieved a high accuracy of 93% using Logitboost for root exploit detection.
• The developed Root Exploit Detection System (RODS) successfully predicted all tested root exploit samples.
• Identified key features within system commands, directory paths, and code for effective malware identification.

Conclusions:

• The proposed system demonstrates significant effectiveness in detecting root exploit malware targeting blockchain environments.
• Logitboost, combined with PSO-selected features, offers a powerful approach for enhancing mobile malware detection accuracy.
• This research contributes to securing sensitive data within blockchain-based medical data management systems against sophisticated threats.