Harris Hawks Feature Selection in Distributed Machine Learning for Secure IoT Environments

TL;DR

This paper introduces a Harris Hawks Optimization-based feature selection method combined with a Random Weight Network to enhance IoT botnet attack detection in distributed machine learning environments, achieving high accuracy and preserving data privacy.

Contribution

It presents a novel feature selection approach using Harris Hawks Optimization integrated with RWN for improved IoT attack detection in distributed ML settings.

Findings

Achieves up to 99.9% F-measure in IoT attack detection

Improves accuracy, precision, recall, and F-measure over existing methods

Distributed ML performs competitively with centralized models

Abstract

The development of the Internet of Things (IoT) has dramatically expanded our daily lives, playing a pivotal role in the enablement of smart cities, healthcare, and buildings. Emerging technologies, such as IoT, seek to improve the quality of service in cognitive cities. Although IoT applications are helpful in smart building applications, they present a real risk as the large number of interconnected devices in those buildings, using heterogeneous networks, increases the number of potential IoT attacks. IoT applications can collect and transfer sensitive data. Therefore, it is necessary to develop new methods to detect hacked IoT devices. This paper proposes a Feature Selection (FS) model based on Harris Hawks Optimization (HHO) and Random Weight Network (RWN) to detect IoT botnet attacks launched from compromised IoT devices. Distributed Machine Learning (DML) aims to train models locally on edge devices without sharing data to a central server. Therefore, we apply the proposed approach using centralized and distributed ML models. Both learning models are evaluated under two benchmark datasets for IoT botnet attacks and compared with other well-known classification techniques using different evaluation indicators. The experimental results show an improvement in terms of accuracy, precision, recall, and F-measure in most cases. The proposed method achieves an average F-measure up to 99.9\%. The results show that the DML model achieves competitive performance against centralized ML while maintaining the data locally.