IoT Botnet Detection and Classification using Machine Learning Algorithms

Phát hiện và phân loại tấn công mạng bằng cách sử dụng các thuật toán học máy

  • Van Quan Pham
  • Van Uc Ngo
  • Phuc Hao Do
  • Năng Hùng Vân Nguyễn
Keywords: Internet of Things, Supervised learning, Intrucsion detection, IoT Botnet, Machine Learning

Abstract

This scholarly research paper addresses the crucial and complex challenge of detecting and categorizing Internet of Things (IoT) botnets through the utilization of machine learning algorithms. The study is focused on conducting meticulous analysis and manipulation of IoT botnet data, with a specific emphasis placed on the widely acknowledged IoT- 23 dataset. The principal aim is to employ widely recognized and widely-used machine learning algorithms, encompassing Decision Trees (DT), k-Nearest Neighbors (KNN), Random Forests (RF), and eXtreme Gradient Boosting (XGBoost), with the purpose of effectively classifying and detecting botnets within the confines of the IoT-23 dataset. By implementing these algorithms, the paper seeks to augment our understanding of their performance and efficacy within the domain of IoT botnet detection and classification. The execution of a comparative analysis, contrasting the outcomes derived from the diverse algorithms, will furnish invaluable insights into their respective merits and constraints, thereby enabling researchers and practitioners to make informed decisions concerning the most suitable algorithm for achieving successful IoT botnet detection and classification.

Author Biographies

Van Quan Pham

Pham Van Quan1[0009-0003-1625-0848], Ngo Van Uc2[0009-0005-0954-5618], Do Phuc Hao3 [0000-
0003-0645-0021], and Nguyen Nang Hung Van4[0000-0002-9963-7006]
1, 2 Dong A University, Da Nang, Vietnam
quan10.work@gmail.com, ngovanuc.1508@gmail.com
3 The Bonch-Bruevich Saint-Petersburg State University of Telecommunications,
Saint-Petersburg, Russian Federation
haodp.sut@gmail.com
4 Danang University of Science and Technology, Da Nang, Vietnam
nguyenvan@dut.udn.vn

Van Uc Ngo

Student at Dong A University in 2020, majoring in Artificial Intelligence and Data Science. His
research interests include machine learning, deep learning, data science, artificial
intelligence, image processing, and their
applications.

Phuc Hao Do

Received his MS degree in Computer science from the University
of Danang - University of Science and
Technology in 2017. He is currently a Ph.D.
student in the Department of Communication Networks and Data Transmission at
the Bonch-Bruevich Saint- Petersburg State
University of Telecommunications, Russia.
His research interests include Artificial Intelligence, Machine
Learning and its application in different fields like network,
blockchain.

Năng Hùng Vân Nguyễn

Nguyen Nang Hung Van4
1 Dong A University, Da Nang, Vietnam
2 The Bonch-Bruevich Saint-Petersburg State University of Telecommunications, Saint-Petersburg, Russian Federation
3 Da Nang University of Architecture, Da Nang, Viet Nam
4 Danang University of Science and Technology, Da Nang, Vietnam

References

Williams, P., Dutta, I.K., Daoud,. H, and Bayoumi, M, A survey on security in internet of things with a focus on the impact of emerging technologies, Elsevier. (2022).

Khan, W.Z., Rehman, M.H., Zangoti, H.M., Afzal, M.K., Armi, N., and Salah, K, Industrial internet of things: Recent advances, enabling technologies and open challenges, Elsevier, 2020..

Vitorino, J., Andrade, R., Prac¸a, I., Sousa, O., and Maia, E, "A Comparative Analysis of Ma-chine Learning Techniques for IoT Intrusion Detection", Foundations and Practice of Security (pp. 191-207), Springer, (2022).

Haq, N.F., Onik, A.R., Hridoy, M.A.K, Rafni, M., Shah, F.M., and Farid, D.M, "Application of Machine Learning Approaches inIntrusion Detection System: A Survey", International Journal of Advanced Research in Artificial Intelligence(IJARAI), Volume 4 Issue 3, (2015).

Hajji, J., Khalily, M., Moustafa, N., and Nelms, T. IoT-23, A Dataset for IoT Network Traffic Analysis, Springer, (2019). [6] Rahim, A., Razzaque, M.A., Hasan, R., and Hossain, M.F, Effective IoT Network Security through Feature Selection and Machine Learning Techniques, IEEE, 2020..

Islam, S.M.Z, Bhuiyan M.Z.H, and Hasan R., Fusion of Machine Learning Models for Intru-sion Detection in IoT Networks using the IoT-23 Dataset, IEEE, 2020.

Li, Y., Qiu, L., Chen, Y., and Chen, Y., Ensemble-based Intrusion Detection System for IoT Networks using the IoT-23 Dataset, IEEE, 2020.

P. H. Do, T. D. Dinh, D. T. Le, V. D. Pham, L. Myrova and R. Kirichek, "An Efficient Fea-ture Extraction Method for Attack Classification in IoT Networks," 13th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), 2021.

Alotaibi, F., Al-Qaness, M.A., Abunadi, A., and Alghazzawi, M.A., A Deep Learning Ap-proach for Intrusion Detection in IoT Networks using the IoT-23 Dataset, IEEE, 2020.

Li, J., Hu, C., Yang, K., Zhang, X., and Lu, J, An IoT-23 based IoT Intrusion Detection Sys-tem using Deep Learning, IEEE, 2020..

Abdallah, A., Khalil, I., Al-Emadi, N., Almohaimeed, A., and Kim, H., Real-Time IoT Botnet Detection Using Deep Learning on IoT-23 Dataset, IEEE, 2020.

Kiani, A.T., Abbas, R.A., Abbasi, A.Z., and Khan, M.K., Deep Learning-based Anomaly De-tection for IoT Networks using the IoT-23 Dataset, IEEE, 2020.

Rasool, S., Saeed, S., Farooq, F., and Madani, A., A Comparative Study of Transfer Learning Approaches for IoT Malware Detection Using IoT-23 Dataset, IEEE, 2021.

Sebastian Garcia, Agustin Parmisano, and Maria Jose Erquiaga, IoT-23: A labeled da-taset with malicious and benign IoT network traffic (Version 1.0.0) [Data set], Zenodo, 2020.

Stoian, N.A., "Machine Learning for Anomaly Detection in IoT Networks : Malware analysis on the IoT-23 data set", EEMCS: Electrical Engineering, Mathematics and Computer Science, 2020.

Published
2023-06-30