Digital Forensics as Advanced Ransomware Pre-Attack Detection Algorithm for Endpoint Data Protection

Abstract

Ransomware is a malicious software that takes files hostage and demands ransomware to release them. It targets individuals, corporations, organizations, and public services such as hospitals and police stations. It is a growing industry that affected more than three million users from 2019 to 2020. The ransom payments totaled 25 billion-plus dollars in the year 2019. The latest version of ransomware was developed using undetectable and nonanalysis techniques. This paper represents an intelligent KNN and density-based machine learning algorithm to detect ransomware pre-attacks on an endpoint system. The data preprocessing and feature engineering techniques are augmented with the KNN algorithm for finding the solution. This helps the anti-malware developer, vendors, endpoint security provider companies, or researchers work on malware detection using advanced machine learning algorithms to develop the more effective ransomware defensive solutions to detect and prevent ransomware pre-attack execution. The proposed KNN and density-based algorithm will predict ransomware detection with higher accuracy than other machine learning algorithms. The anti-malware and anti-ransomware solution provider companies can use this algorithm to improve their existing ransomware detection solutions for endpoint users.