A Framework for AI-Driven Cyber Threat Detection in Critical Infrastructure
1 Department of Computing, Coventry University, UK.
2 Department of Computer Science, Fourah Bay University, Sierra Leone.
Research Article
World Journal of Advanced Research and Reviews, 2019, 03(03), 165-170
Publication history:
Received on 11 July 2019; revised on 13 October 2019; accepted on 29 October 2019
Abstract:
This paper presents a research framework for AI-driven cyber threat detection to enhance the security of critical national infrastructure. In response to the escalating sophistication of cyberattacks, which render traditional reactive defenses inadequate, this study develops and evaluates a comprehensive artificial intelligence methodology. The framework systematically integrates heterogeneous data streams, employs feature engineering and machine learning models, including deep neural networks for real-time anomaly detection, and incorporates automated response protocols. Novel contributions include the exploration of a quantum-enhanced anomaly scoring mechanism based on state fidelity. Empirical results from operational simulations demonstrate the system's high efficacy, achieving 97.3% detection accuracy, a 1.8% false-positive rate, and sub-three-second threat containment. A comparative analysis further examines the performance-cost trade-offs of emerging quantum encryption. The study concludes that deploying such AI-powered, proactive defense systems is a strategic imperative for nations like Ghana, offering a pragmatic pathway to cyber resilience while planning for a quantum-resilient future
Keywords:
Cyberattacks; Anomaly detection; Artificial intelligence; Neural networks; Quantum encryption
Full text article in PDF:
Copyright information:
Copyright © 2019 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0