Explainable AI for Risk-Aware Cybersecurity Decision Intelligence: A Data-Driven Framework for Human-Governed Decision Support

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

This preprint presents an explainable artificial intelligence framework for risk-aware cybersecurity decision intelligence and human-governed decision support. The study investigates how machine-learning predictions can be transformed into interpretable risk levels that support cybersecurity decision-making while preserving human oversight. Using the UNSW-NB15 intrusion-detection dataset, multiple machine-learning models are evaluated using classification and ranking metrics, with explainability methods used to identify influential features behind model predictions. The proposed framework integrates predictive analytics, explainable AI, risk-aware interpretation, and human governance to bridge the gap between automated cyber-threat prediction and actionable decision support. The study contributes a reproducible approach for examining how AI-generated cybersecurity predictions can support transparent and accountable risk-based decisions rather than functioning solely as automated classification outputs.