Malicious Traffic Detection in IoT and Local Networks Using Stacked Ensemble Classifier

作     者：R.D.Pubudu L.Indrasiri Ernesto Lee Vaibhav Rupapara Furqan Rustam Imran Ashraf 

作者机构：School of Computing and MathematicsCharles Sturt UniversityAustralia Department of Computer ScienceBroward CollegeBroward CountyFloridaUSA School of Computing and Information SciencesFlorida International UniversityUSA Department of Computer ScienceKhwaja Fareed University of Engineering and Information TechnologyRahim Yar KhanPakistan Department of Information and Communication EngineeringYeungnam UniversityGyeongsan-si38541Korea 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2022年第71卷第4期

页      面：489-515页

核心收录：

学科分类：0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 

基　　金：Funding Statement: This research was supported by the Florida Center for Advanced and Data Science funded by Ernesto.Net (under the Algorithms for Good Grant) 

主　　题：Stacked ensemble PCA malicious traffic detection classification machine learning 

摘      要：Malicious traffic detection over the internet is one of the challenging areas for researchers to protect network infrastructures from any malicious *** shortcomings of a network system can be leveraged by an attacker to get unauthorized access through malicious *** from such attacks requires an efficient automatic system that can detect malicious traffic timely and avoid system ***,many automated systems can detect malicious activity,however,the efficacy and accuracy need further improvement to detect malicious traffic from multi-domain *** present study focuses on the detection of malicious traffic with high accuracy using machine learning *** proposed approach used two datasets UNSW-NB15 and IoTID20 which contain the data for IoT-based traffic and local network traffic,*** datasets were combined to increase the capability of the proposed approach in detecting malicious traffic from local and IoT networks,with high *** merging both datasets requires an equal number of features which was achieved by reducing feature count to 30 for each dataset by leveraging principal component analysis(PCA).The proposed model incorporates stacked ensemble model extra boosting forest(EBF)which is a combination of tree-based models such as extra tree classifier,gradient boosting classifier,and random forest using a stacked ensemble *** results show that EBF performed significantly better and achieved the highest accuracy score of 0.985 and 0.984 on the multi-domain dataset for two and four classes,respectively.