Generative AI for Cybersecurity Awareness Training

Human errors remain one of the leading causes of cybersecurity breaches during the rapid growth of cyber-attack techniques recently, underscoring the need for adaptive and personalized training programs. Traditional Cybersecurity Awareness Training (CSAT) programs often rely on static content, lack of personalization, and struggle remain in the face of evolving threats. This study presents an AI driven CSAT framework that integrates Generative Artificial Intelligence (GAI), Online Machine Learning, and adaptive data processing to deliver personalized, scalable, and real-time training contents. The proposed model utilizes GAI to dynamically generate interactive training contents tailored to individual user profiles based on job roles, behavioural risk indicators, impact assessment scores, and the pre-assessment outcomes. An online Naïve Bayes algorithm enables continuous risk profiling and content adaptation according to user performance, while windowing technique and integrated search engine ensure up-to-date and contextually relevant training materials. The proposed system aligns with Bloom’s Taxonomy and MITRE ATT&CK framework to ensure cognitive depth and real-world attack vector relevance. The research demonstrates that the integration of GAI with adaptive learning technologies significantly improves knowledge retention, enhance user engagement, and delivers cost-effective training solution. Further this study highlights the potential of GAI in revolutionizing cybersecurity training, ensuring resilience against evolving cyber-threats.