• 2026-05-08
• M. Agagu
• Volume 2, Issue 1

Abstract

Ransomware attacks have become one of the most destructive cybersecurity threats facing organizations worldwide, causing significant financial losses, operational disruptions, and data breaches. Traditional security mechanisms such as antivirus software, firewalls, and single-factor authentication systems are increasingly insufficient against sophisticated ransomware campaigns that exploit compromised credentials and weak access control mechanisms. Multifactor Authentication (MFA) has emerged as an effective solution for strengthening identity verification; however, most existing MFA implementations remain static and do not incorporate intelligent mechanisms for detecting suspicious behaviour after successful authentication. This study proposes the development of an intelligent multifactor authentication system integrated with a machine learning-based threat detection module for proactive ransomware prevention. The proposed system combines three authentication factors: password authentication, one-time password (OTP) verification, and biometric validation. In addition to identity verification, the system continuously monitors behavioural indicators such as login patterns, device characteristics, IP geolocation, and typing dynamics. Machine learning algorithms, including Random Forest, Support Vector Machines (SVM), and Artificial Neural Networks (ANN), were evaluated for anomaly detection. Experimental results demonstrate that the Random Forest model achieved the highest performance with a ransomware detection accuracy of 95%, significantly outperforming traditional single-factor authentication systems. The proposed framework provides a proactive and adaptive cybersecurity solution capable of identifying suspicious authentication activities before ransomware attacks can propagate within a system. The findings highlight the importance of integrating behavioural analytics with multifactor authentication to strengthen enterprise cybersecurity resilience against evolving cyber threats.