Leveraging Artificial Intelligence and Machine Learning: Enhancing Cybersecurity Framework for Educational Institutions

Abstract

The increasing digitalization of educational institutions has enhanced various processes but has also exposed them to sophisticated cyber threats, such as phishing, ransomware, and advanced persistent threats. This study explores how artificial intelligence (AI) and machine learning (ML) techniques can be utilized to enhance the detection and mitigation of cyber threats in educational settings. Building upon previous research that proposed a framework for cyber threat intelligence (CTI) sharing among colleges in Camarines Norte using the Malware Information Sharing Platform (MISP) and Amazon Web Services (AWS), this paper integrates AI/ML techniques into the existing framework to strengthen cybersecurity measures.

An exploratory qualitative research design was adopted, involving a systematic literature review of publications from 2010 to 2023. The data were analyzed using thematic, comparative, and SWOT analyses to identify current AI/ML techniques, evaluate their integration with existing cybersecurity frameworks, and assess their theoretical benefits and challenges.

Findings indicate that unsupervised learning algorithms, deep learning models, and federated learning approaches are practical AI/ML techniques suitable for educational institutions, particularly those with limited data resources. The integration of AI/ML into the existing CTI framework enhances threat detection accuracy, enables real-time analysis, and supports adaptive learning.

The study concludes that integrating AI/ML techniques into the existing cybersecurity framework significantly enhances cyber threat detection and mitigation in educational institutions. By strategically adopting these technologies and addressing implementation challenges, educational institutions can improve their cybersecurity posture, protect sensitive data, and maintain the integrity of their digital infrastructure.