Research on Network Intrusion Detection Based on Incremental Extreme Learning Machine and Adaptive Principal Component Analysis

Abstract

Recently, network attacks launched by malicious attackers have seriously affected modern life and enterprise production, and these network attack samples have the characteristic of type imbalance, which undoubtedly increases the difficulty of intrusion detection. In response to this problem, it would naturally be very meaningful to design an intrusion detection system (IDS) to effectively and quickly identify and detect malicious behaviors. In our work, we have proposed a method for an IDS-combined incremental extreme learning machine (I-ELM) with an adaptive principal component (A-PCA). In this method, the relevant features of network traffic are adaptively selected, where the best detection accuracy can then be obtained by I-ELM. We have used the NSL-KDD standard dataset and UNSW-NB15 standard dataset to evaluate the performance of our proposed method. Through analysis of the experimental results, we can see that our proposed method has better computation capacity, stronger generalization ability, and higher accuracy.

Performance Analysis of Intrusion Detection Systems Using a Feature Selection Method on the UNSW-NB15 Dataset

“…Gao et al [30] proposed an IDS using an incremental approach of the Extreme Learning Machine (IELM) in conjunction with an Advanced Principal Component (APCA) algorithm. The APCA has the role to adaptively select the most relevant features required by the IELM so as to perform an optimal attack prediction.…”

Intrusion Detection System Based on Gradient Corrected Online Sequential Extreme Learning Machine

“…Some researchers have integrated ELM with feature reduction algorithms, namely principle component analysis (PCA) for boosting performance and reducing computational time. This is done in the work of [29], where an adaptive PCA was used with ELM. However, this is regarded as a direct implementation of ELM without any handling of the random weights issue of ELM.…”

An Advanced Pruning Method in the Architecture of Extreme Learning Machines Using L1-Regularization and Bootstrapping

“…Cybersecurity is also aided by models trained with ELM and feature selection methods. In the Gao et al [37] model, an ELM incremental model combined with Adaptive Principal Component Analysis concepts is used to determine patterns of intrusions and intruders in computer networks. In the context of models using ELMs, Campos Souza et al [38] built a model that performs pruning of less significant neurons using the concepts of Automatic Relevance Determination.…”