ISSN: 2582-8266 (Online) || ISSN Approved Journal || Google Scholar Indexed || Impact Factor: 9.48 || Crossref DOI
AI-driven threat modeling for critical infrastructure
Independent Publisher, USA.
Research Article
World Journal of Advanced Engineering Technology and Sciences, 2024, 13(01), 1142-1155.
Article DOI: 10.30574/wjaets.2024.13.1.0476
Publication history:
Received on 24 August 2024; revised on 27 September 2024; accepted on 29 September 2024
Abstract:
The research investigates how Artificial Intelligence (AI) enhances the security of vital national and global infrastructure through threat modeling systems evaluation. The main research goal is to evaluate how well AI-based systems detect infrastructure weaknesses while reducing security threats affecting power grids, transportation, and healthcare services and facilities. The research depends on case study approaches combined with an assessment of AI implementations through real-world scenarios, machine learning algorithms, and anomaly detection methods. The analysis reveals AI succeeds in advancing threat identification and speed of response yet demonstrates obstacles because of system combination demands, data privacy risks, and fake alarms in systems. Universal threat modeling built on AI foundations represents the solution that provides adjustable and comprehensive security protection for the evolving complex cyber threats that target our critical infrastructure. The study presents valuable research inputs to teams and creates new ways of viewing infrastructure defense protocol changes from AI while specifying future research progression paths. Research efforts need to address three fundamental challenges related to AI integration along with precision modeling and ethical development for proper implementation.
Keywords:
AI cybersecurity; Threat modeling; Critical infrastructure; Anomaly detection; Machine learning; Smart systems
Full text article in PDF:
Copyright information:
Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0