IoT Botnet Detection Using Various One-Class Classifiers
Nowadays, the Internet of Things (IoT) is a common word for the people because of its increasing number of users. Statistical results show that the users of IoT devices are dramatically increasing, and in the future, it will be to an ever-increasing extent. Because of the increasing number of users,...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
World Scientific Publishing
2021-05-01
|
Series: | Vietnam Journal of Computer Science |
Subjects: | |
Online Access: | http://www.worldscientific.com/doi/epdf/10.1142/S2196888821500123 |
id |
doaj-5f8f563b727542cf88b3fe3189226bae |
---|---|
record_format |
Article |
spelling |
doaj-5f8f563b727542cf88b3fe3189226bae2021-02-01T10:41:54ZengWorld Scientific PublishingVietnam Journal of Computer Science2196-88882196-88962021-05-018229131010.1142/S219688882150012310.1142/S2196888821500123IoT Botnet Detection Using Various One-Class ClassifiersMehedi Hasan Raj0A. N. M. Asifur Rahman1Umma Habiba Akter2Khayrun Nahar Riya3Anika Tasneem Nijhum4Rashedur M. Rahman5Department of Electrical and Computer Engineering, North South University, Plot 15, Block-B, Bashundhara, Dhaka 1229, BangladeshDepartment of Electrical and Computer Engineering, North South University, Plot 15, Block-B, Bashundhara, Dhaka 1229, BangladeshDepartment of Electrical and Computer Engineering, North South University, Plot 15, Block-B, Bashundhara, Dhaka 1229, BangladeshDepartment of Electrical and Computer Engineering, North South University, Plot 15, Block-B, Bashundhara, Dhaka 1229, BangladeshDepartment of Electrical and Computer Engineering, North South University, Plot 15, Block-B, Bashundhara, Dhaka 1229, BangladeshDepartment of Electrical and Computer Engineering, North South University, Plot 15, Block-B, Bashundhara, Dhaka 1229, BangladeshNowadays, the Internet of Things (IoT) is a common word for the people because of its increasing number of users. Statistical results show that the users of IoT devices are dramatically increasing, and in the future, it will be to an ever-increasing extent. Because of the increasing number of users, security experts are now concerned about its security. In this research, we would like to improve the security system of IoT devices, particularly in IoT botnet, by applying various machine learning (ML) techniques. In this paper, we have set up an approach to detect botnet of IoT devices using three one-class classifier ML algorithms. The algorithms are: one-class support vector machine (OCSVM), elliptic envelope (EE), and local outlier factor (LOF). Our method is a network flow-based botnet detection technique, and we use the input packet, protocol, source port, destination port, and time as features of our algorithms. After a number of preprocessing steps, we feed the preprocessed data to our algorithms that can achieve a good precision score that is approximately 77–99%. The one-class SVM achieves the best accuracy score, approximately 99% in every dataset, and EE’s accuracy score varies from 91% to 98%; however, the LOF factor achieves lowest accuracy score that is from 77% to 99%. Our algorithms are cost-effective and provide good accuracy in short execution time.http://www.worldscientific.com/doi/epdf/10.1142/S2196888821500123botnetiot botnetcybersecurityddos attackone-class classifiersupport vector machineelliptic envelopelocal outlier factor |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Mehedi Hasan Raj A. N. M. Asifur Rahman Umma Habiba Akter Khayrun Nahar Riya Anika Tasneem Nijhum Rashedur M. Rahman |
spellingShingle |
Mehedi Hasan Raj A. N. M. Asifur Rahman Umma Habiba Akter Khayrun Nahar Riya Anika Tasneem Nijhum Rashedur M. Rahman IoT Botnet Detection Using Various One-Class Classifiers Vietnam Journal of Computer Science botnet iot botnet cybersecurity ddos attack one-class classifier support vector machine elliptic envelope local outlier factor |
author_facet |
Mehedi Hasan Raj A. N. M. Asifur Rahman Umma Habiba Akter Khayrun Nahar Riya Anika Tasneem Nijhum Rashedur M. Rahman |
author_sort |
Mehedi Hasan Raj |
title |
IoT Botnet Detection Using Various One-Class Classifiers |
title_short |
IoT Botnet Detection Using Various One-Class Classifiers |
title_full |
IoT Botnet Detection Using Various One-Class Classifiers |
title_fullStr |
IoT Botnet Detection Using Various One-Class Classifiers |
title_full_unstemmed |
IoT Botnet Detection Using Various One-Class Classifiers |
title_sort |
iot botnet detection using various one-class classifiers |
publisher |
World Scientific Publishing |
series |
Vietnam Journal of Computer Science |
issn |
2196-8888 2196-8896 |
publishDate |
2021-05-01 |
description |
Nowadays, the Internet of Things (IoT) is a common word for the people because of its increasing number of users. Statistical results show that the users of IoT devices are dramatically increasing, and in the future, it will be to an ever-increasing extent. Because of the increasing number of users, security experts are now concerned about its security. In this research, we would like to improve the security system of IoT devices, particularly in IoT botnet, by applying various machine learning (ML) techniques. In this paper, we have set up an approach to detect botnet of IoT devices using three one-class classifier ML algorithms. The algorithms are: one-class support vector machine (OCSVM), elliptic envelope (EE), and local outlier factor (LOF). Our method is a network flow-based botnet detection technique, and we use the input packet, protocol, source port, destination port, and time as features of our algorithms. After a number of preprocessing steps, we feed the preprocessed data to our algorithms that can achieve a good precision score that is approximately 77–99%. The one-class SVM achieves the best accuracy score, approximately 99% in every dataset, and EE’s accuracy score varies from 91% to 98%; however, the LOF factor achieves lowest accuracy score that is from 77% to 99%. Our algorithms are cost-effective and provide good accuracy in short execution time. |
topic |
botnet iot botnet cybersecurity ddos attack one-class classifier support vector machine elliptic envelope local outlier factor |
url |
http://www.worldscientific.com/doi/epdf/10.1142/S2196888821500123 |
work_keys_str_mv |
AT mehedihasanraj iotbotnetdetectionusingvariousoneclassclassifiers AT anmasifurrahman iotbotnetdetectionusingvariousoneclassclassifiers AT ummahabibaakter iotbotnetdetectionusingvariousoneclassclassifiers AT khayrunnaharriya iotbotnetdetectionusingvariousoneclassclassifiers AT anikatasneemnijhum iotbotnetdetectionusingvariousoneclassclassifiers AT rashedurmrahman iotbotnetdetectionusingvariousoneclassclassifiers |
_version_ |
1724315517765812224 |