Generative AI and LLMs for Critical Infrastructure Protection: Evaluation Benchmarks, Agentic AI, Challenges, and Opportunities

Yagmur Yigit; Mohamed Amine Ferrag; Mohamed C. Ghanem; Iqbal H. Sarker; Leandros A. Maglaras; Christos Chrysoulas; Naghmeh Moradpoor; Norbert Tihanyi; Helge Janicke

doi:10.3390/s25061666

Generative AI and LLMs for Critical Infrastructure Protection: Evaluation Benchmarks, Agentic AI, Challenges, and Opportunities

Yagmur Yigit, Mohamed Amine Ferrag, Mohamed C. Ghanem, Iqbal H. Sarker, Leandros A. Maglaras, Christos Chrysoulas, Naghmeh Moradpoor, Norbert Tihanyi, Helge Janicke

Research output: Contribution to journal › Article › peer-review

16 Downloads (Pure)

Abstract

Critical National Infrastructures (CNIs)—including energy grids, water systems, transportation networks, and communication frameworks—are essential to modern society yet face escalating cybersecurity threats. This review paper comprehensively analyzes AI-driven approaches for Critical Infrastructure Protection (CIP). We begin by examining the reliability of CNIs and introduce established benchmarks for evaluating Large Language Models (LLMs) within cybersecurity contexts. Next, we explore core cybersecurity issues, focusing on trust, privacy, resilience, and securability in these vital systems. Building on this foundation, we assess the role of Generative AI and LLMs in enhancing CIP and present insights on applying Agentic AI for proactive defense mechanisms. Finally, we outline future directions to guide the integration of advanced AI methodologies into protecting critical infrastructures. Our paper provides a strategic roadmap for researchers and practitioners committed to fortifying national infrastructures against emerging cyber threats through this synthesis of current challenges, benchmarking strategies, and innovative AI applications.

Original language	English
Article number	1666
Journal	Sensors
Volume	25
Issue number	6
DOIs	https://doi.org/10.3390/s25061666
Publication status	Published - 7 Mar 2025

Keywords

critical infrastructure protection
critical national infrastructure
reliability
security

ASJC Scopus subject areas

Analytical Chemistry
Information Systems
Atomic and Molecular Physics, and Optics
Biochemistry
Instrumentation
Electrical and Electronic Engineering

Access to Document

10.3390/s25061666Licence: CC BY

Download pdf
© 2025 by the authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/)
Final published version, 695 KBLicence: CC BY

Cite this

@article{db4467e0a6d944c086865271df516c25,

title = "Generative AI and LLMs for Critical Infrastructure Protection: Evaluation Benchmarks, Agentic AI, Challenges, and Opportunities",

abstract = "Critical National Infrastructures (CNIs)—including energy grids, water systems, transportation networks, and communication frameworks—are essential to modern society yet face escalating cybersecurity threats. This review paper comprehensively analyzes AI-driven approaches for Critical Infrastructure Protection (CIP). We begin by examining the reliability of CNIs and introduce established benchmarks for evaluating Large Language Models (LLMs) within cybersecurity contexts. Next, we explore core cybersecurity issues, focusing on trust, privacy, resilience, and securability in these vital systems. Building on this foundation, we assess the role of Generative AI and LLMs in enhancing CIP and present insights on applying Agentic AI for proactive defense mechanisms. Finally, we outline future directions to guide the integration of advanced AI methodologies into protecting critical infrastructures. Our paper provides a strategic roadmap for researchers and practitioners committed to fortifying national infrastructures against emerging cyber threats through this synthesis of current challenges, benchmarking strategies, and innovative AI applications.",

keywords = "critical infrastructure protection, critical national infrastructure, reliability, security",

author = "Yagmur Yigit and Ferrag, {Mohamed Amine} and Ghanem, {Mohamed C.} and Sarker, {Iqbal H.} and Maglaras, {Leandros A.} and Christos Chrysoulas and Naghmeh Moradpoor and Norbert Tihanyi and Helge Janicke",

year = "2025",

month = mar,

day = "7",

doi = "10.3390/s25061666",

language = "English",

volume = "25",

journal = "Sensors",

issn = "1424-8220",

publisher = "MDPI",

number = "6",

}

TY - JOUR

T1 - Generative AI and LLMs for Critical Infrastructure Protection: Evaluation Benchmarks, Agentic AI, Challenges, and Opportunities

AU - Yigit, Yagmur

AU - Ferrag, Mohamed Amine

AU - Ghanem, Mohamed C.

AU - Sarker, Iqbal H.

AU - Maglaras, Leandros A.

AU - Chrysoulas, Christos

AU - Moradpoor, Naghmeh

AU - Tihanyi, Norbert

AU - Janicke, Helge

PY - 2025/3/7

Y1 - 2025/3/7

N2 - Critical National Infrastructures (CNIs)—including energy grids, water systems, transportation networks, and communication frameworks—are essential to modern society yet face escalating cybersecurity threats. This review paper comprehensively analyzes AI-driven approaches for Critical Infrastructure Protection (CIP). We begin by examining the reliability of CNIs and introduce established benchmarks for evaluating Large Language Models (LLMs) within cybersecurity contexts. Next, we explore core cybersecurity issues, focusing on trust, privacy, resilience, and securability in these vital systems. Building on this foundation, we assess the role of Generative AI and LLMs in enhancing CIP and present insights on applying Agentic AI for proactive defense mechanisms. Finally, we outline future directions to guide the integration of advanced AI methodologies into protecting critical infrastructures. Our paper provides a strategic roadmap for researchers and practitioners committed to fortifying national infrastructures against emerging cyber threats through this synthesis of current challenges, benchmarking strategies, and innovative AI applications.

AB - Critical National Infrastructures (CNIs)—including energy grids, water systems, transportation networks, and communication frameworks—are essential to modern society yet face escalating cybersecurity threats. This review paper comprehensively analyzes AI-driven approaches for Critical Infrastructure Protection (CIP). We begin by examining the reliability of CNIs and introduce established benchmarks for evaluating Large Language Models (LLMs) within cybersecurity contexts. Next, we explore core cybersecurity issues, focusing on trust, privacy, resilience, and securability in these vital systems. Building on this foundation, we assess the role of Generative AI and LLMs in enhancing CIP and present insights on applying Agentic AI for proactive defense mechanisms. Finally, we outline future directions to guide the integration of advanced AI methodologies into protecting critical infrastructures. Our paper provides a strategic roadmap for researchers and practitioners committed to fortifying national infrastructures against emerging cyber threats through this synthesis of current challenges, benchmarking strategies, and innovative AI applications.

KW - critical infrastructure protection

KW - critical national infrastructure

KW - reliability

KW - security

UR - http://www.scopus.com/inward/record.url?scp=105001128168&partnerID=8YFLogxK

U2 - 10.3390/s25061666

DO - 10.3390/s25061666

M3 - Article

SN - 1424-8220

VL - 25

JO - Sensors

JF - Sensors

IS - 6

M1 - 1666

ER -

Generative AI and LLMs for Critical Infrastructure Protection: Evaluation Benchmarks, Agentic AI, Challenges, and Opportunities

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this