A Comparative Study of Drone GPS Spoofing Detection Algorithm Between Naïve Bayes and Artificial Neural Network

Authors

  • Nurul Ain Wahida Azaha Universiti Tun Hussein Onn Malaysia
  • Shamsul Kamal Ahmad Khalid Universiti Tun Hussein Onn Malaysia

Keywords:

GPS Spoofing, Machine Learning, Deep Learning, Naïve Bayes, Artificial Neural Network

Abstract

Global Positioning System (GPS) spoofing attack overwhelms a target Unmanned Arial Vehicle (UAV) or drone by sending spoof data to interrupt the location of the drone. Researchers have done many works in overcoming the GPS spoofing attack yet the performance analysis of some of the common methods are not available. In this study, the Naïve Bayes and Artificial Neural Network (ANN) classification and detection of GPS spoofing are analyzed. The experiment was carried out and tested on UAV Attack dataset. The experiments cover several performance metrics like True Positive Rate, False Positive Rate, Error rate and accuracy in identifying the best performance classifiers. At the end of the study, the ANN classifiers are identified to be best classifiers with 85.55% of accuracy compared to Naïve Bayes classifiers with 74.58% of accuracy.

Downloads

Published

22-11-2021

How to Cite

Nurul Ain Wahida Azaha, & Shamsul Kamal Ahmad Khalid. (2021). A Comparative Study of Drone GPS Spoofing Detection Algorithm Between Naïve Bayes and Artificial Neural Network. Applied Information Technology And Computer Science, 2(2), 141–154. Retrieved from https://publisher.uthm.edu.my/periodicals/index.php/aitcs/article/view/2261

Issue

Section

Information Security