Feature extraction for machine learning-based intrusion detection in IoT networks

作     者：Mohanad Sarhan Siamak Layeghy Nour Moustafa Marcus Gallagher Marius Portmann Mohanad Sarhan;Siamak Layeghy;Nour Moustafa;Marcus Gallagher;Marius Portmann

作者机构：University of QueenslandBrisbaneQLD4072Australia University of New South WalesCanberraACT2612Australia 

出 版 物：《Digital Communications and Networks》 (数字通信与网络（英文版）)

年 卷 期：2024年第10卷第1期

页      面：205-216页

核心收录：

学科分类：1305[艺术学-设计学（可授艺术学、工学学位）] 12[管理学] 13[艺术学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0804[工学-仪器科学与技术] 0835[工学-软件工程] 081101[工学-控制理论与控制工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Feature extraction Machine learning Network intrusion detection system IoT 

摘      要：A large number of network security breaches in IoT networks have demonstrated the unreliability of current Network Intrusion Detection Systems(NIDSs).Consequently,network interruptions and loss of sensitive data have occurred,which led to an active research area for improving NIDS *** an analysis of related works,it was observed that most researchers aim to obtain better classification results by using a set of untried combinations of Feature Reduction(FR)and Machine Learning(ML)techniques on NIDS ***,these datasets are different in feature sets,attack types,and network ***,this paper aims to discover whether these techniques can be generalised across various *** ML models are utilised:a Deep Feed Forward(DFF),Convolutional Neural Network(CNN),Recurrent Neural Network(RNN),Decision Tree(DT),Logistic Regression(LR),and Naive Bayes(NB).The accuracy of three Feature Extraction(FE)algorithms is detected;Principal Component Analysis(PCA),Auto-encoder(AE),and Linear Discriminant Analysis(LDA),are evaluated using three benchmark datasets:UNSW-NB15,ToN-IoT and *** PCA and AE algorithms have been widely used,the determination of their optimal number of extracted dimensions has been *** results indicate that no clear FE method or ML model can achieve the best scores for all *** optimal number of extracted dimensions has been identified for each dataset,and LDA degrades the performance of the ML models on two *** variance is used to analyse the extracted dimensions of LDA and ***,this paper concludes that the choice of datasets significantly alters the performance of the applied *** believe that a universal(benchmark)feature set is needed to facilitate further advancement and progress of research in this field.