Big Data Approach For IoT Botnet Traffic Detection Using Apache Spark Technology

Arokodare Oluwatomisin; Hayden Wimmer; Jie Du

doi:10.1109/CCWC57344.2023.10099385

Big Data Approach For IoT Botnet Traffic Detection Using Apache Spark Technology

Arokodare Oluwatomisin, Hayden Wimmer, Jie Du

Information Technology

Research output: Contribution to book or proceeding › Conference article › peer-review

1 Scopus citations

Abstract

In recent years, numerous machine learning classifiers have been applied to improve network infiltration. Due to the exponential growth of data, new technologies are needed to handle such massive amounts of data in a timely manner. The machine learning classifiers are trained on datasets for intrusion detection. In this study, we used the feature selection technique to choose the best dataset characteristics for machine learning and then performed binary classification to distinguish the intrusive traffic from the normal one using four machine learning algorithms, including Decision Tree, Support Vector Machine, Random Forest, and Naive Bayes in the UNSW-NB15 data set on Apache Spark framework. The performance of classifiers is evaluated in terms of accuracy, precision, recall, and F1-score for a comparative analysis of the various machine learning classifiers.

Original language	American English
Title of host publication	IEEE 13th Annual Computing and Communication Workshop and Conference, CCWC 2023
Editors	Rajashree Paul
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1260-1266
Number of pages	7
ISBN (Electronic)	9798350332865
DOIs	https://doi.org/10.1109/CCWC57344.2023.10099385 https://doi.org/10.1109/CCWC57344.2023.10099385
State	Published - Apr 18 2023
Event	IEEE Annual Computing and Communication Workshop and Conference - Virtual, Online Duration: Mar 8 2023 → Mar 11 2023 Conference number: 13 https://ieeexplore.ieee.org/servlet/opac?punumber=10099037

Publication series

Name	IEEE Annual Computing and Communication Workshop and Conference (CCWC) Proceedings

Conference

Conference	IEEE Annual Computing and Communication Workshop and Conference
Abbreviated title	CCWC
Period	03/8/23 → 03/11/23
Internet address	https://ieeexplore.ieee.org/servlet/opac?punumber=10099037

Scopus Subject Areas

Artificial Intelligence
Computer Networks and Communications
Computer Science Applications
Computer Vision and Pattern Recognition
Information Systems and Management
Control and Optimization
Instrumentation

Disciplines

Computer Sciences

Keywords

Big Data
Botnet
Cluster computing
Conferences
Intrusion detection
Machine learning algorithms
Support vector machines

Access to Document

10.1109/CCWC57344.2023.10099385
10.1109/CCWC57344.2023.10099385License: Unspecified

https://doi.org/10.1109/CCWC57344.2023.10099385

Cite this

Oluwatomisin, A., Wimmer, H., & Du, J. (2023). Big Data Approach For IoT Botnet Traffic Detection Using Apache Spark Technology. In R. Paul (Ed.), IEEE 13th Annual Computing and Communication Workshop and Conference, CCWC 2023 (pp. 1260-1266). (IEEE Annual Computing and Communication Workshop and Conference (CCWC) Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CCWC57344.2023.10099385, https://doi.org/10.1109/CCWC57344.2023.10099385

Oluwatomisin, Arokodare ; Wimmer, Hayden ; Du, Jie. / Big Data Approach For IoT Botnet Traffic Detection Using Apache Spark Technology. IEEE 13th Annual Computing and Communication Workshop and Conference, CCWC 2023. editor / Rajashree Paul. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 1260-1266 (IEEE Annual Computing and Communication Workshop and Conference (CCWC) Proceedings).

@inproceedings{803c39a00e1a487d800a5f279923f62c,

title = "Big Data Approach For IoT Botnet Traffic Detection Using Apache Spark Technology",

abstract = "In recent years, numerous machine learning classifiers have been applied to improve network infiltration. Due to the exponential growth of data, new technologies are needed to handle such massive amounts of data in a timely manner. The machine learning classifiers are trained on datasets for intrusion detection. In this study, we used the feature selection technique to choose the best dataset characteristics for machine learning and then performed binary classification to distinguish the intrusive traffic from the normal one using four machine learning algorithms, including Decision Tree, Support Vector Machine, Random Forest, and Naive Bayes in the UNSW-NB15 data set on Apache Spark framework. The performance of classifiers is evaluated in terms of accuracy, precision, recall, and F1-score for a comparative analysis of the various machine learning classifiers.",

keywords = "Big Data, Botnet, Cluster computing, Conferences, Intrusion detection, Machine learning algorithms, Support vector machines",

author = "Arokodare Oluwatomisin and Hayden Wimmer and Jie Du",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; IEEE Annual Computing and Communication Workshop and Conference, CCWC ; Conference date: 08-03-2023 Through 11-03-2023",

year = "2023",

month = apr,

day = "18",

doi = "10.1109/CCWC57344.2023.10099385",

language = "American English",

series = "IEEE Annual Computing and Communication Workshop and Conference (CCWC) Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1260--1266",

editor = "Rajashree Paul",

booktitle = "IEEE 13th Annual Computing and Communication Workshop and Conference, CCWC 2023",

address = "United States",

url = "https://ieeexplore.ieee.org/servlet/opac?punumber=10099037",

}

Oluwatomisin, A, Wimmer, H & Du, J 2023, Big Data Approach For IoT Botnet Traffic Detection Using Apache Spark Technology. in R Paul (ed.), IEEE 13th Annual Computing and Communication Workshop and Conference, CCWC 2023. IEEE Annual Computing and Communication Workshop and Conference (CCWC) Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 1260-1266, IEEE Annual Computing and Communication Workshop and Conference, 03/8/23. https://doi.org/10.1109/CCWC57344.2023.10099385, https://doi.org/10.1109/CCWC57344.2023.10099385

Big Data Approach For IoT Botnet Traffic Detection Using Apache Spark Technology. / Oluwatomisin, Arokodare; Wimmer, Hayden; Du, Jie.
IEEE 13th Annual Computing and Communication Workshop and Conference, CCWC 2023. ed. / Rajashree Paul. Institute of Electrical and Electronics Engineers Inc., 2023. p. 1260-1266 (IEEE Annual Computing and Communication Workshop and Conference (CCWC) Proceedings).

Research output: Contribution to book or proceeding › Conference article › peer-review

TY - GEN

T1 - Big Data Approach For IoT Botnet Traffic Detection Using Apache Spark Technology

AU - Oluwatomisin, Arokodare

AU - Wimmer, Hayden

AU - Du, Jie

N1 - Conference code: 13

PY - 2023/4/18

Y1 - 2023/4/18

N2 - In recent years, numerous machine learning classifiers have been applied to improve network infiltration. Due to the exponential growth of data, new technologies are needed to handle such massive amounts of data in a timely manner. The machine learning classifiers are trained on datasets for intrusion detection. In this study, we used the feature selection technique to choose the best dataset characteristics for machine learning and then performed binary classification to distinguish the intrusive traffic from the normal one using four machine learning algorithms, including Decision Tree, Support Vector Machine, Random Forest, and Naive Bayes in the UNSW-NB15 data set on Apache Spark framework. The performance of classifiers is evaluated in terms of accuracy, precision, recall, and F1-score for a comparative analysis of the various machine learning classifiers.

AB - In recent years, numerous machine learning classifiers have been applied to improve network infiltration. Due to the exponential growth of data, new technologies are needed to handle such massive amounts of data in a timely manner. The machine learning classifiers are trained on datasets for intrusion detection. In this study, we used the feature selection technique to choose the best dataset characteristics for machine learning and then performed binary classification to distinguish the intrusive traffic from the normal one using four machine learning algorithms, including Decision Tree, Support Vector Machine, Random Forest, and Naive Bayes in the UNSW-NB15 data set on Apache Spark framework. The performance of classifiers is evaluated in terms of accuracy, precision, recall, and F1-score for a comparative analysis of the various machine learning classifiers.

KW - Big Data

KW - Botnet

KW - Cluster computing

KW - Conferences

KW - Intrusion detection

KW - Machine learning algorithms

KW - Support vector machines

UR - https://digitalcommons.georgiasouthern.edu/information-tech-facpubs/162

UR - https://doi.org/10.1109/CCWC57344.2023.10099385

U2 - 10.1109/CCWC57344.2023.10099385

DO - 10.1109/CCWC57344.2023.10099385

M3 - Conference article

AN - SCOPUS:85156200166

T3 - IEEE Annual Computing and Communication Workshop and Conference (CCWC) Proceedings

SP - 1260

EP - 1266

BT - IEEE 13th Annual Computing and Communication Workshop and Conference, CCWC 2023

A2 - Paul, Rajashree

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE Annual Computing and Communication Workshop and Conference

Y2 - 8 March 2023 through 11 March 2023

ER -

Oluwatomisin A, Wimmer H, Du J. Big Data Approach For IoT Botnet Traffic Detection Using Apache Spark Technology. In Paul R, editor, IEEE 13th Annual Computing and Communication Workshop and Conference, CCWC 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 1260-1266. (IEEE Annual Computing and Communication Workshop and Conference (CCWC) Proceedings). doi: 10.1109/CCWC57344.2023.10099385, 10.1109/CCWC57344.2023.10099385

Big Data Approach For IoT Botnet Traffic Detection Using Apache Spark Technology

Abstract

Publication series

Conference

Scopus Subject Areas

Disciplines

Keywords

Access to Document

Other files and links

Fingerprint

Cite this