An AI-Driven Framework for Intelligent Intrusion Detection and Network Traffic Analysis

View Sample PDF

Author(s): Alvaro Guarnido (Illinois Institute of Technology, USA & Universidad Politecnica de Madrid, Spain)and Paul Nyamohanga (Illinois Institute of Technology, USA)
Copyright: 2026
Pages: 30
Source title: Examining Vulnerabilities and Adversarial Exploitation of AI and LLMs
Source Author(s)/Editor(s): Puya Pakshad (Illinois Institute of Technology, USA)and Marwan Omar (Illinois Institute of Technology, USA)
DOI: 10.4018/979-8-3373-8252-4.ch008

Keywords: Artificial Intelligence / Engineering Science Reference / Information Security & Privacy / Security & Forensics

Purchase

View An AI-Driven Framework for Intelligent Intrusion Detection and Network Traffic Analysis on the publisher's website for pricing and purchasing information.

Abstract

This research project presents an AI-based intrusion detection framework for smart renewable energy grids. It enhances the traditional binary detection to a multi-class model capable of identifying different types of cyberattacks, including DoS, malware, phishing, MITM, SQL injection and zero-day. The proposed system utilizes the Smart Grid Intrusion Detection Dataset. It combines the Random Forest with the Autoencoder machine learning models to reach an accuracy of 97.8%, with the objective of minimizing false positives. Temporal analysis is included in order to discover attack patterns across hours, days of the week and operational phases of the energy grids. In addition, this project trains an XGBoost predictive model to determine attack likelihood or type based on recent temporal sequences. The study contributes to a predictive cybersecurity approach, anticipating attacks and strengthening resilience in intelligent energy infrastructures.

The IRMA Community

Research IRM

An AI-Driven Framework for Intelligent Intrusion Detection and Network Traffic Analysis

Purchase

Abstract

Related Content

IRMA Sponsors