Optimized Cyber Attack Detection in IoT Networks Using Feature Selection and LightGBM

Akshat Gaurav, Brij B. Gupta, Kwok Tai Chui

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

Abstract

The spread of IoT networks presents major security issues, especially with regard to identifying and reducing cyberattacks. In this context, we proposed an optimal LightGBM model for IoT network cyber attack detection. We used Random Forest classifier to find optimal features. Then LightGBM is trained on the selected features. After this the LightGBM model was tested against eleven conventional machine learning models. With the greatest accuracy (9 9. 8%), F1 score (9 9. 8%), precision (9 9. 8%), and recall (9 9. 8%), the LightGBM model clearly outperformed other machine learning models.

Original languageEnglish
Title of host publication27th International Symposium on Wireless Personal Multimedia Communications, WPMC 2024
ISBN (Electronic)9798350392319
DOIs
Publication statusPublished - 2024
Event27th International Symposium on Wireless Personal Multimedia Communications, WPMC 2024 - Greater Noida, India
Duration: 17 Nov 202420 Nov 2024

Publication series

NameInternational Symposium on Wireless Personal Multimedia Communications, WPMC
ISSN (Print)1347-6890

Conference

Conference27th International Symposium on Wireless Personal Multimedia Communications, WPMC 2024
Country/TerritoryIndia
CityGreater Noida
Period17/11/2420/11/24

Keywords

  • Cyber Attack Detection
  • Feature Selection
  • IoT Security
  • LightGBM

Fingerprint

Dive into the research topics of 'Optimized Cyber Attack Detection in IoT Networks Using Feature Selection and LightGBM'. Together they form a unique fingerprint.

Cite this