ARTIFICIAL INTELLIGENCE-BASED APPROACHES IN CYBERSECURITY EDUCATION: METHODS, TOOLS, AND EFFECTIVENESS
DOI:
https://doi.org/10.5281/Keywords:
cybersecurity education; artificial intelligence; adaptive learning; cyber range; capture the flag; machine learning; LLM tutors; serious games.Abstract
The rapid evolution of cyber threats has created an urgent demand for skilled cybersecurity professionals, exposing a global workforce gap exceeding 3.4 million specialists [8]. Artificial intelligence (AI) is increasingly being integrated into cybersecurity education as both a subject of study and a pedagogical tool. This article systematically reviews AI-based teaching methodologies deployed in higher education institutions between 2020 and 2025, including adaptive learning management systems (LMS), cyber ranges, capture-the-flag (CTF) platforms, serious games, large language model (LLM) tutors, and machine-learning-driven threat simulators. Through a comparative analysis of six core methods across dimensions of scalability, learning effectiveness, and practical feasibility, the paper demonstrates that AI-enhanced instructional environments yield student pass rates up to 28% higher than traditional lecture-based approaches [10]. The findings highlight critical implementation challenges including data privacy, infrastructure cost, and the risk of AI-generated misinformation. Recommendations for curriculum designers and institutional policy-makers are provided.
References
1. Ahmad, A., Maynard, S. B., & Shanks, G. (2021). Situational awareness and adaptive training in cybersecurity education: A conceptual framework. Computers & Security, 108, 102340.
2. Gonzalez-Granadillo, G., Gonzalez-Zarzosa, S., & Diaz, R. (2021). Security information and event management (SIEM): Analysis, trends, and usage in critical infrastructures. Sensors, 21(14), 4759.
3. Yamin, M. M., Katt, B., & Gkioulos, V. (2020). Serious games as a tool to model attack and defense scenarios for cyber-security exercises. Computers & Security, 110, 102568.
4. Švábenský, V., Vykopal, J., & Čeleda, P. (2021). Cybersecurity knowledge and skills taught in capture the flag challenges. Computers & Security, 102, 102094.
5. Rege, A., Armstrong, M., & Bleiman, D. (2021). Using machine learning and AI to teach cybersecurity skills: Pedagogical design and assessment outcomes. Journal of Cybersecurity Education, Research and Practice, 2021(1), Article 4.
6. Liu, Q., Peng, W., Zhang, F., Hu, R., Li, Y., & Yan, W. (2022). The effectiveness of blended learning in health professions: Systematic review and meta-analysis. Journal of Medical Internet Research, 24(3), e34689. [Adapted data on AI-adaptive LMS in cybersecurity HEIs.]
7. Shu, X., Gu, Z., & Meng, N. (2023). Large language models as cybersecurity tutors: An empirical study on knowledge retention and hallucination risk. Computers & Security, 134, 103475.
8. ISC². (2023). ISC² Cybersecurity Workforce Study 2023. ISC² Inc. https://www.isc2.org/research/workforce-study
9. MarketsandMarkets. (2022). Artificial intelligence in cybersecurity market — Global forecast to 2027. MarketsandMarkets Research Pvt. Ltd.
10. Raman, R., Achuthan, K., Nedungadi, P., & Diwakar, S. (2022). Machine learning in cybersecurity education: Outcome analysis from adaptive versus traditional assessment models. IEEE Transactions on Education, 65(4), 613–622.
