Enhancing Cybersecurity Awareness using Machine Learning Algorithms

This study employs machine learning techniques to classify malware threats using the CTDAPD dataset, which encompasses diverse malware characteristics enabling comprehensive pattern identification and threat categorization. Decision tree algorithms were selected for their interpretability and capability to handle complex attribute interactions effectively. Experimental results demonstrate high classification accuracy across malware categories, providing actionable insights for cybersecurity professionals. The model identifies critical features influencing malware behavior, thereby facilitating proactive defense strategies. Beyond technical contributions, this research underscores the significance of machine learning in cybersecurity education and awareness. Decision path visualization enhances user comprehension of malware indicators, enabling informed decision-making and reducing system vulnerabilities. The proposed framework contributes to both theoretical understanding of malware classification and practical applications in threat detection. Future research will explore integration with real-time detection systems to enhance the framework's operational applicability and scalability across diverse cybersecurity environments. These advancements aim to strengthen organizational resilience against evolving cyber threats through intelligent, interpretable classification models.

Al-Rawahi, N. A., Al-Rajhi, M. S., & Mathivanan, V. (2026). Enhancing cybersecurity awareness using machine learning algorithms. Journal of Applied AI and Smart Technologies, 1(1), 1–8.