AI-Driven Intelligent Attack Detection for IoT Networks Using Big Data and Machine Learning

  • Akshat Gaurav
  • , Razaz Waheeb Attar
  • , Varsha Arya
  • , Arcangelo Castiglione
  • , Kwok Tai Chui

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

With the exponential growth of IoT networks, ensuring robust security has become increasingly critical, as these systems are vulnerable to various cyberattacks. Traditional methods often struggle to handle the massive data generated by IoT devices. This paper introduces an AI-driven, big data approach to intelligent attack detection for IoT networks. Utilizing the NSLKDD dataset, we employed PySpark for preprocessing and chi-square-based feature selection to identify the 15 most significant features, optimizing performance and reducing computational costs. The proposed model, based on XGBoost, achieved outstanding classification results with 98.93% accuracy, and precision, recall, and F1-score approaching 99%. Comparative analysis against models like Random Forest and LightGBM confirmed its effectiveness, providing a scalable, accurate solution for IoT security.

Original languageEnglish
Title of host publicationICC 2025 - IEEE International Conference on Communications
EditorsMatthew Valenti, David Reed, Melissa Torres
Pages2599-2604
Number of pages6
ISBN (Electronic)9798331505219
DOIs
Publication statusPublished - 2025
Event2025 IEEE International Conference on Communications, ICC 2025 - Montreal, Canada
Duration: 8 Jun 202512 Jun 2025

Publication series

NameIEEE International Conference on Communications
ISSN (Print)1550-3607

Conference

Conference2025 IEEE International Conference on Communications, ICC 2025
Country/TerritoryCanada
CityMontreal
Period8/06/2512/06/25

Keywords

  • Attack Detection
  • Big Data Analytics
  • IoT Security
  • Machine Learning

Fingerprint

Dive into the research topics of 'AI-Driven Intelligent Attack Detection for IoT Networks Using Big Data and Machine Learning'. Together they form a unique fingerprint.

Cite this