Random Forest and One-vs-Rest Classification for Malware and Ransomware Detection
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
The rapid evolution of malware and ransomware has reduced the effectiveness of conventional signature-based and heuristic detection systems.This study proposes a malware detection approach based on Random Forest Classifier (RFC) and One-vs-Rest (OvR) multiclass classification to improve the identification of diverse cyber threats.The proposed approach integrates Synthetic Minority Oversampling Technique (SMOTE)-based data balancing, feature selection using Random Forest (RF) feature importance, Principal Component Analysis (PCA), and preprocessing optimization to enhance model generalization and reduce false detections.The method was evaluated on a dataset containing nine attack categories, including Distributed Denial of Service (DDoS), Denial of Service (DoS), Structured Query Language (SQL) injection, phishing, and ransomware.Experimental results show that RFC achieved an accuracy of 95%, while the OvR classifier reached 97% in multiclass threat identification.Precision, recall, F1-score, Receiver Operating Characteristic (ROC) curves, and confusion matrices further demonstrate the reliability and discriminative ability of the proposed approach.The findings indicate that the model provides an efficient, scalable, and interpretable solution for malware and ransomware detection in endpoint security environments.
Fields of Study & Subjects
Advanced Malware Detection Techniques
Network Security and Intrusion Detection
Spam and Phishing Detection
Publication details
- Journal / source
- International Journal of Safety and Security Engineering
- Volume
- 16
- Issue
- 1
- Pages
- 95–104
- Publication date
- 31 January 2026
- Language
- EN