An Effective Networks Intrusion Detection Approach Based on Hybrid Harris Hawks and Multi-Layer Perceptron

TL;DR

This paper introduces a hybrid Harris Hawks and Multi-Layer Perceptron approach for network intrusion detection, optimizing parameters with evolutionary algorithms to improve accuracy and detection of malicious patterns.

Contribution

The paper presents a novel hybrid HHO-MLP model that outperforms other evolutionary algorithms in intrusion detection accuracy and efficiency.

Findings

Achieved 93.17% accuracy in intrusion detection.

Outperformed other evolutionary algorithms like BOA, GOA, BOW.

Demonstrated high sensitivity and specificity in identifying malicious patterns.

Abstract

This paper proposes an Intrusion Detection System (IDS) employing the Harris Hawks Optimization algorithm (HHO) to optimize Multilayer Perceptron learning by optimizing bias and weight parameters. HHO-MLP aims to select optimal parameters in its learning process to minimize intrusion detection errors in networks. HHO-MLP has been implemented using EvoloPy NN framework, an open-source Python tool specialized for training MLPs using evolutionary algorithms. For purposes of comparing the HHO model against other evolutionary methodologies currently available, specificity and sensitivity measures, accuracy measures, and mse and rmse measures have been calculated using KDD datasets. Experiments have demonstrated the HHO MLP method is effective at identifying malicious patterns. HHO-MLP has been tested against evolutionary algorithms like Butterfly Optimization Algorithm (BOA), Grasshopper Optimization Algorithms (GOA), and Black Widow Optimizations (BOW), with validation by Random Forest (RF), XG-Boost. HHO-MLP showed superior performance by attaining top scores with accuracy rate of 93.17%, sensitivity level of 89.25%, and specificity percentage of 95.41%.