DDoS ATTACK DETECTION SCHEME USING HYBRID ENSEMBLE LEARNING AND GA ALGORITHM FOR INTERNET OF THINGS

Authors

  • Amin Erfan

Abstract

Methods: In this paper, we using the hybrid feature selection GA algorithm (GA) and ensemble learning system such as C4.5 decision tree, deep neural network (DNN) and K-KNN (KNN) algorithm for IoT. The GA feature selection used for selecting best attribute on DDoS attacks dataset and from ensemble learning system is for DDoS attach detection.

Results: To validate the proposed method, the results were compared with other approaches, including machine learning methods that combined with other optimization methods. We used 10% of the KDDCup99 dataset for simulation. The results of the paper show the high accuracy of the proposed method for DDoS attacks detection compared to other recent methods of about 5%.

Conclusions: Therefore, by presenting experiments to DDoS attacks detection, it was observed that the proposed method detected the DDoS with acceptable accuracy and the combination of ensemble learning methods and GA feature selection algorithm was successful.

Downloads

Download data is not yet available.

Downloads

Published

2022-01-03

How to Cite

Amin Erfan. (2022). DDoS ATTACK DETECTION SCHEME USING HYBRID ENSEMBLE LEARNING AND GA ALGORITHM FOR INTERNET OF THINGS. PalArch’s Journal of Archaeology of Egypt / Egyptology, 18(18), 521-546. Retrieved from https://www.archives.palarch.nl/index.php/jae/article/view/10546