perpus@umsida.ac.id +62-31-8945444

Mir, Jawad Yaqoob and Mir, Fawad (2026) Artificial Intelligence for Secure Cloud-Native Critical Infrastructure: Improving National Cyber Resilience, Operational Reliability, and Economic Security. International Journal of Mathematical Theory and Computer Science Issues, 3 (1).

[img] Text
Matematichal_Artificial+Intelligence+for+Secure.pdf

Download (545kB)
Official URL: https://academicajournal.com/IJMTCSI/article/view/...

Abstract

Critical infrastructure increasingly depends on cloud-native technologies, including containers, microservices, Kubernetes, application programming interfaces, distributed cloud platforms, and automated software-delivery pipelines. Although these technologies improve scalability and service availability, their dynamic architecture, machine identities, third-party components, and complex dependencies create cybersecurity and operational risks that can cascade across essential national services. Existing approaches often address cloud-native security, AI-based threat detection, operational reliability, business continuity, economic-risk assessment, and governance separately. This fragmentation leaves a gap for a unified, service-centered framework that connects technical security events with mission-critical dependencies, operational consequences, human decision authority, and wider economic impacts. This study proposes the Artificial Intelligence-Enabled Cloud-Native Critical Infrastructure Resilience Framework (AI-CNCI-RF) as a conceptual design-science artifact. The framework integrates cybersecurity governance, critical-service and dependency intelligence, secure cloud-native engineering, zero-trust access control, trusted telemetry, AI-assisted detection and prediction, controlled incident response, trusted recovery, and economic-risk assessment. Its novelty lies in combining technical cybersecurity evidence with service criticality, cascading dependencies, data quality, operational reliability, economic consequences, and risk-controlled automation. AI is positioned as an explainable decision-support capability, while high-impact actions remain subject to policy constraints, safety gates, and human authorization. Theoretically, AI-CNCI-RF unifies previously fragmented domains of cloud-native security and resilience. Practically, it provides a phased implementation and governance roadmap. Operationally, it supports risk prioritization, earlier detection, reversible response, service continuity, and verified recovery. Because the framework is conceptual and not yet empirically validated, future work should test its variables, thresholds, indicators, and effectiveness through prototypes, simulations, cyber exercises, controlled experiments, and sector-specific deployments.

Item Type: Article
Uncontrolled Keywords: artificial intelligence, cloud-native security, critical infrastructure, cyber resilience, operational reliability
Subjects: H Social Sciences
Depositing User: admin eprints
Date Deposited: 05 Nov 2026 09:01
Last Modified: 05 Nov 2026 09:01
URI: http://eprints.umsida.ac.id/id/eprint/17505

Actions (login required)

View Item View Item