An Ensemble Learning Based Intrusion Detection Model for Industrial IoT Security
作者机构:Technology Higher SchoolCadi Ayyad UniversityEssaouira 44000Morocco IDMS TeamFaculty of Sciences and TechniquesMoulay Ismail University of MeknesErrachidia 52000Morocco
出 版 物:《Big Data Mining and Analytics》 (大数据挖掘与分析(英文))
年 卷 期:2023年第6卷第3期
页 面:273-287页
核心收录:
学科分类:12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 0839[工学-网络空间安全] 08[工学] 081104[工学-模式识别与智能系统] 0714[理学-统计学(可授理学、经济学学位)] 0835[工学-软件工程] 0701[理学-数学] 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:Industrial Internet of Things(IIoT) isolation forest Intrusion Detection Dystem(IDS) intrusion Pearson’s Correlation Coefficient(PCC) random forest
摘 要:Industrial Internet of Things(IIoT)represents the expansion of the Internet of Things(IoT)in industrial *** is designed to implicate embedded technologies in manufacturing fields to enhance their ***,IIoT involves some security vulnerabilities that are more damaging than those of ***,Intrusion Detection Systems(IDSs)have been developed to forestall inevitable harmful *** survey the environment to identify intrusions in real *** study designs an intrusion detection model exploiting feature engineering and machine learning for IIoT *** combine Isolation Forest(IF)with Pearson’s Correlation Coefficient(PCC)to reduce computational cost and prediction *** is exploited to detect and remove outliers from *** apply PCC to choose the most appropriate *** and IF are applied exchangeably(PCCIF and IFPCC).The Random Forest(RF)classifier is implemented to enhance IDS *** evaluation,we use the Bot-IoT and NF-UNSW-NB15-v2 ***-PCCIF and RF-IFPCC show noteworthy results with 99.98%and 99.99%Accuracy(ACC)and 6.18 s and 6.25 s prediction time on Bot-IoT,*** two models also score 99.30%and 99.18%ACC and 6.71 s and 6.87 s prediction time on NF-UNSW-NB15-v2,*** prove that our designed model has several advantages and higher performance than related models.