Network intrusion detection system for Internet of Things based on enhanced flower pollination algorithm and ensemble classifier

In the Internet of Things environment, the intrusion detection involves identification of distributed denial of service attacks in the network traffic which is aimed at improving network security. Recently, several methods have been developed for network anomaly detection which is generally based on the conventional machine learning techniques. The existing methods completely rely on manual traffic features which increases the system complexity and results in a lower detection rate on large traffic datasets. To overcome these issues, a new intrusion detection system is proposed based on the enhanced flower pollination algorithm (EFPA) and ensemble classification technique. First, the optimal set of features is selected from the UNSW-NB15 and NSL-KDD datasets by using EFPA. In the EFPA, a scaling factor is used in the conventional FPA for optimal feature selection and better convergence, and the selected features are fed to the ensemble classifier for network attack detection. The ensemble classifier aims to learn a set of classifiers such as random forest, decision tree (ID3), and support vector machine classifiers and then votes the best results. In the resulting section, the proposed ensemble-based EFPA model attained 99.32% and 99.67% of accuracy on UNSW-NB15 and NSL-KDD datasets, respectively, and these obtained results are more superior compared to the traditional network intrusion detection models. The proposed and the existing models are validated on the anaconda-navigator and Python 3.6 software environment.

Automated summary

The study introduces a new intrusion detection system based on the enhanced flower pollination algorithm (EFPA) and ensemble classification technique, achieving an accuracy of 99.32% and 99.67% on the UNSW-NB15 and NSL-KDD datasets, respectively, outperforming traditional network intrusion detection models.