AI-Driven Anomaly Detection in Critical Infrastructure

EasyChair Preprint 14553

Abstract

Critical infrastructure, such as power grids, water distribution systems, and transportation networks, forms the backbone of modern society. The increasing complexity and interconnectivity of these systems make them vulnerable to a range of threats, including cyber-attacks, equipment failures, and natural disasters. Traditional monitoring and anomaly detection approaches often fall short in identifying unusual patterns or predicting failures in real time.

This paper explores the application of artificial intelligence (AI)-driven anomaly detection techniques in safeguarding critical infrastructure. AI models, particularly those based on machine learning and deep learning, can analyze vast amounts of data, identify patterns, and detect anomalies that deviate from expected behavior. These models offer the potential for real-time monitoring, improved accuracy in anomaly detection, and early warning systems that can prevent catastrophic failures.

Keyphrases: AI-driven, Critical Infrastructure, anomaly detection

@booklet{EasyChair:14553,
  author    = {Favour Olaoye and Kaledio Potter},
  title     = {AI-Driven Anomaly Detection in Critical Infrastructure},
  howpublished = {EasyChair Preprint 14553},
  year      = {EasyChair, 2024}}