A Hybrid Fuzzy-ML Model for Analysing Cybersecurity Awareness and Risk Perception in Higher Education

The growth of digital platforms in higher education institutions has increased cybersecurity dangers, hence requiring advanced models for risk analysis and mitigation. Conventional machine learning models, although efficient, frequently encounter difficulties with complex data and indicate a lack of interpretability. This study presents a hybrid fuzzy-ML model that integrates fuzzy logic and machine learning to evaluate cybersecurity awareness and risk perception. The fuzzy logic component manages uncertain input using linguistic variables, whereas the machine learning component identifies complex patterns and improves predictive precision. This hybrid model attained an accuracy of 97.2%, precision of 96.5%, recall of 97.1%, and an F1-score of 96.8%, outperforming baseline models including logistic regression and SVM. The suggested system offers a resilient, understandable, and data-informed methodology for detecting cybersecurity threats. This model outperforms previous methods in terms of performance and adaptability, providing higher education institutions with an effective means to counter cyber-attacks and improve digital security.

Перевод пока недоступен