Learning-Tree Based Network Intrusion Detection for IoT

Ishaan Mishra; Shalaka S. Mahadik; Pranav M. Pawar; Raja Muthalagu; R. Elakkiya; Nanadkumar Kulkarni

doi:10.1109/ic3i59117.2023.10398156

Learning-Tree Based Network Intrusion Detection for IoT

Ishaan Mishra, Shalaka S. Mahadik, Pranav M. Pawar, Raja Muthalagu, R. Elakkiya, Nanadkumar Kulkarni

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The Internet of Things (IoT) is an emerging technology utilized by many devices worldwide to communicate and share information. The interaction of these devices ex- poses the network to cyberattacks that could exploit system vulnerabilities and result in disastrous consequences. Intelligent intrusion detection systems (IDS) are gaining prominence as they can actively analyze network traffic and classify it as normal or hostile activity. These IDS can be developed by employing machine learning (ML) techniques. As a result, the research aimed to develop robust learning-tree-based ML techniques and assess each technique's performance. The research investigations emitted remarkable outcomes, with the random forest (RF) and decision tree (DT) algorithms lending an accuracy of 99% each. Furthermore, the research highlighted the optimal depth of the tree for both algorithms, with favorable and efficient outcomes that show how lightweight and less complex the proposed learning-tree-based network IDS is in the context of IoT.

Original language	English
Title of host publication	Proceedings of International Conference on Contemporary Computing and Informatics, IC3I 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	756-761
Number of pages	6
ISBN (Electronic)	9798350304480
DOIs	https://doi.org/10.1109/ic3i59117.2023.10398156
State	Published - 2023
Externally published	Yes
Event	6th International Conference on Contemporary Computing and Informatics, IC3I 2023 - Gautam Buddha Nagar, India Duration: 14 Sep 2023 → 16 Sep 2023

Publication series

Name	Proceedings of International Conference on Contemporary Computing and Informatics, IC3I 2023

Conference

Conference	6th International Conference on Contemporary Computing and Informatics, IC3I 2023
Country/Territory	India
City	Gautam Buddha Nagar
Period	14/09/23 → 16/09/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

BoT-IoT
Decision tree
Intrusion detection system
Machine learning
Random forest

Access to Document

10.1109/ic3i59117.2023.10398156

Cite this

Mishra, I., Mahadik, S. S., Pawar, P. M., Muthalagu, R., Elakkiya, R., & Kulkarni, N. (2023). Learning-Tree Based Network Intrusion Detection for IoT. In Proceedings of International Conference on Contemporary Computing and Informatics, IC3I 2023 (pp. 756-761). (Proceedings of International Conference on Contemporary Computing and Informatics, IC3I 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ic3i59117.2023.10398156

Mishra, Ishaan ; Mahadik, Shalaka S. ; Pawar, Pranav M. et al. / Learning-Tree Based Network Intrusion Detection for IoT. Proceedings of International Conference on Contemporary Computing and Informatics, IC3I 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 756-761 (Proceedings of International Conference on Contemporary Computing and Informatics, IC3I 2023).

@inproceedings{606b82985a0045e0812bd70089108e7c,

title = "Learning-Tree Based Network Intrusion Detection for IoT",

abstract = "The Internet of Things (IoT) is an emerging technology utilized by many devices worldwide to communicate and share information. The interaction of these devices ex- poses the network to cyberattacks that could exploit system vulnerabilities and result in disastrous consequences. Intelligent intrusion detection systems (IDS) are gaining prominence as they can actively analyze network traffic and classify it as normal or hostile activity. These IDS can be developed by employing machine learning (ML) techniques. As a result, the research aimed to develop robust learning-tree-based ML techniques and assess each technique's performance. The research investigations emitted remarkable outcomes, with the random forest (RF) and decision tree (DT) algorithms lending an accuracy of 99% each. Furthermore, the research highlighted the optimal depth of the tree for both algorithms, with favorable and efficient outcomes that show how lightweight and less complex the proposed learning-tree-based network IDS is in the context of IoT.",

keywords = "BoT-IoT, Decision tree, Intrusion detection system, Machine learning, Random forest",

author = "Ishaan Mishra and Mahadik, {Shalaka S.} and Pawar, {Pranav M.} and Raja Muthalagu and R. Elakkiya and Nanadkumar Kulkarni",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 6th International Conference on Contemporary Computing and Informatics, IC3I 2023 ; Conference date: 14-09-2023 Through 16-09-2023",

year = "2023",

doi = "10.1109/ic3i59117.2023.10398156",

language = "אנגלית",

series = "Proceedings of International Conference on Contemporary Computing and Informatics, IC3I 2023",

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

pages = "756--761",

booktitle = "Proceedings of International Conference on Contemporary Computing and Informatics, IC3I 2023",

address = "ארצות הברית",

}

Mishra, I, Mahadik, SS, Pawar, PM, Muthalagu, R, Elakkiya, R & Kulkarni, N 2023, Learning-Tree Based Network Intrusion Detection for IoT. in Proceedings of International Conference on Contemporary Computing and Informatics, IC3I 2023. Proceedings of International Conference on Contemporary Computing and Informatics, IC3I 2023, Institute of Electrical and Electronics Engineers Inc., pp. 756-761, 6th International Conference on Contemporary Computing and Informatics, IC3I 2023, Gautam Buddha Nagar, India, 14/09/23. https://doi.org/10.1109/ic3i59117.2023.10398156

Learning-Tree Based Network Intrusion Detection for IoT. / Mishra, Ishaan; Mahadik, Shalaka S.; Pawar, Pranav M. et al.
Proceedings of International Conference on Contemporary Computing and Informatics, IC3I 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 756-761 (Proceedings of International Conference on Contemporary Computing and Informatics, IC3I 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Learning-Tree Based Network Intrusion Detection for IoT

AU - Mishra, Ishaan

AU - Mahadik, Shalaka S.

AU - Pawar, Pranav M.

AU - Muthalagu, Raja

AU - Elakkiya, R.

AU - Kulkarni, Nanadkumar

PY - 2023

Y1 - 2023

N2 - The Internet of Things (IoT) is an emerging technology utilized by many devices worldwide to communicate and share information. The interaction of these devices ex- poses the network to cyberattacks that could exploit system vulnerabilities and result in disastrous consequences. Intelligent intrusion detection systems (IDS) are gaining prominence as they can actively analyze network traffic and classify it as normal or hostile activity. These IDS can be developed by employing machine learning (ML) techniques. As a result, the research aimed to develop robust learning-tree-based ML techniques and assess each technique's performance. The research investigations emitted remarkable outcomes, with the random forest (RF) and decision tree (DT) algorithms lending an accuracy of 99% each. Furthermore, the research highlighted the optimal depth of the tree for both algorithms, with favorable and efficient outcomes that show how lightweight and less complex the proposed learning-tree-based network IDS is in the context of IoT.

AB - The Internet of Things (IoT) is an emerging technology utilized by many devices worldwide to communicate and share information. The interaction of these devices ex- poses the network to cyberattacks that could exploit system vulnerabilities and result in disastrous consequences. Intelligent intrusion detection systems (IDS) are gaining prominence as they can actively analyze network traffic and classify it as normal or hostile activity. These IDS can be developed by employing machine learning (ML) techniques. As a result, the research aimed to develop robust learning-tree-based ML techniques and assess each technique's performance. The research investigations emitted remarkable outcomes, with the random forest (RF) and decision tree (DT) algorithms lending an accuracy of 99% each. Furthermore, the research highlighted the optimal depth of the tree for both algorithms, with favorable and efficient outcomes that show how lightweight and less complex the proposed learning-tree-based network IDS is in the context of IoT.

KW - BoT-IoT

KW - Decision tree

KW - Intrusion detection system

KW - Machine learning

KW - Random forest

UR - http://www.scopus.com/inward/record.url?scp=85187303800&partnerID=8YFLogxK

U2 - 10.1109/ic3i59117.2023.10398156

DO - 10.1109/ic3i59117.2023.10398156

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85187303800

T3 - Proceedings of International Conference on Contemporary Computing and Informatics, IC3I 2023

SP - 756

EP - 761

BT - Proceedings of International Conference on Contemporary Computing and Informatics, IC3I 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 6th International Conference on Contemporary Computing and Informatics, IC3I 2023

Y2 - 14 September 2023 through 16 September 2023

ER -

Mishra I, Mahadik SS, Pawar PM, Muthalagu R, Elakkiya R, Kulkarni N. Learning-Tree Based Network Intrusion Detection for IoT. In Proceedings of International Conference on Contemporary Computing and Informatics, IC3I 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 756-761. (Proceedings of International Conference on Contemporary Computing and Informatics, IC3I 2023). doi: 10.1109/ic3i59117.2023.10398156

Learning-Tree Based Network Intrusion Detection for IoT

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this