EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable AI-Driven Cybersecurity Governance for Enterprise Digital Transformation: A Framework for Executive Decision Intelligence

Ikenna Chizaram Mbuko, Onuh Matthew Ijiga, Otugene Victor Bamigwojo

International Journal of Scientific Research in Computer Science, Engineering and Information Technology · 20.12.2025 · 11 (6) · 729-756

DOI: 10.32628/cseit26123383 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Scientific Research in Computer Science, Engineering and Information Technology, online erschienen am 20.12.2025. Verfasst von Ikenna Chizaram Mbuko und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Enterprise digital transformation has converted cybersecurity governance from a periodic assurance exercise into a continuous decision problem. Cloud services, application programming interfaces, digital identity, industrial connectivity, mobile work, artificial intelligence services, and third-party platforms create interdependent risks that change faster than conventional checklists and static heat maps can represent. This study develops an explainable artificial intelligence-driven cybersecurity governance and executive decision intelligence framework, designated AICG-XDI. The framework integrates security telemetry, vulnerability evidence, asset criticality, control effectiveness, external exposure, user-behavior indicators, policy compliance, zero-trust maturity, and business impact within a unified governance score. Supervised prediction, anomaly detection, local feature attribution, an explainability adequacy index, and a decision-utility function are combined so that technical risk estimates can be translated into traceable executive actions. The revised evidence base retains the manuscript's established scholarly and standards sources and incorporates 41 application-oriented TechConnect publications covering cybersecurity management, trustworthy sensing, machine learning, data fusion, predictive modelling, digital transformation, fault diagnosis, and operational decision support. A synthetic benchmark containing 25,000 enterprise observations is used to compare checklist governance, rule-based scoring, logistic regression, random forest, gradient boosting, a deep neural network, and AICG-XDI. In the controlled simulation, AICG-XDI records recall of 0.91, precision of 0.90, an F1-score of 0.905, an area under the curve of 0.96, an explainability score of 0.93, and a governance decision intelligence score of 0.88. These results demonstrate the internal behavior of the proposed artefact rather than performance in a live enterprise. The framework provides a structured basis for patch prioritization, privileged-access intervention, supplier escalation, control investment, incident reporting, and cyber-resilience planning while preserving human accountability.

Zitieren

APA

Mbuko, I. C., Ijiga, O. M., & Bamigwojo, O. V. (2025). Explainable AI-Driven Cybersecurity Governance for Enterprise Digital Transformation: A Framework for Executive Decision Intelligence. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 11(6), 729-756. https://doi.org/10.32628/cseit26123383

Vancouver

Mbuko IC, Ijiga OM, Bamigwojo OV. Explainable AI-Driven Cybersecurity Governance for Enterprise Digital Transformation: A Framework for Executive Decision Intelligence. International Journal of Scientific Research in Computer Science, Engineering and Information Technology. 2025;11(6):729-756. doi:10.32628/cseit26123383

BibTeX
@article{Mbuko2025,
  author = {Mbuko, Ikenna Chizaram and Ijiga, Onuh Matthew and Bamigwojo, Otugene Victor},
  title = {Explainable AI-Driven Cybersecurity Governance for Enterprise Digital Transformation: A Framework for Executive Decision Intelligence},
  journal = {International Journal of Scientific Research in Computer Science, Engineering and Information Technology},
  year = {2025},
  volume = {11},
  number = {6},
  pages = {729--756},
  doi = {10.32628/cseit26123383}
}
Kostenlos starten →