Abstract
Artificial intelligence (AI) plays an increasingly important role in security, particularly in view of constantly evolving adversarial tactics and techniques. For Critical Infrastructures (CIs), the demand for AI-based security solutions is essential in an increasingly connected world of heterogeneous CI devices and through evolution of attack vectors. We study how AI could provide better CI security and prevent cyber-attacks. An extensive survey of popular AI models currently adopted for intrusion/attack detection, privacy, trust management, and authentication for CIs is presented. We also propose use cases to describe how AI is used to enable zero trust in industrial control systems and to provide cyber resilience. Based on the study, we also elaborate upon some prominent challenges which must be addressed in the future for adopting reliable and trusted AI for CI security.
| Original language | English |
|---|---|
| Pages (from-to) | 136-142 |
| Number of pages | 7 |
| Journal | IEEE Internet of Things Magazine |
| Volume | 7 |
| Issue number | 4 |
| DOIs | |
| State | Published - Jul 1 2024 |
Bibliographical note
Publisher Copyright:© 2018 IEEE.
ASJC Scopus subject areas
- Software
- Computer Networks and Communications
- Computer Science Applications
- Hardware and Architecture
- Information Systems