AI-driven cybersecurity in higher education: A systematic review and model evaluation for enhanced threat detection and incident response

Cybersecurity threats in higher education institutions (HEIs) are escalating rapidly, as universities confront heightened risks from ransomware attacks, data breaches, and insider threats. Artificial Intelligence (AI) is transforming the world and can significantly contribute to the implementation of cybersecurity measures. Conventional cybersecurity approaches are inadequate in addressing emerging threats, necessitating AI-driven solutions that swiftly identify risks, implement automated response systems, and guarantee compliance enforcement. Despite the burgeoning interest in AI-driven cybersecurity due to technological advancements, a substantial research vacuum exists regarding their application and efficacy in higher education environments. Currently, available literatures emphasize generic AI applications in cybersecurity, resulting in a gap in research that particularly tackles the distinct difficulties encountered by educational institutions. This study addresses this gap by comprehensively assessing the contributions of machine learning and deep learning models (Random Forest, Decision Trees, Support Vector Machine (SVM), Recurrent Neural Network (RNN), and Convolutional Neural Network (CNN)) in cybersecurity for higher education institutions (HEIs). This research utilizes an analysis of AI- driven security models trained on publicly accessible cybersecurity datasets to offer empirical insights into AI's capacity to improve threat detection and incident response. The results underscore AI's capacity to diminish false positives, enhance detection precision, and streamline automated security measures. This study advances AI-based cybersecurity frameworks in higher education institutions, informing future research and policy development for the incorporation of AI-driven threat mitigation measures in academic settings.