NORMA eResearch @NCI Library

Ensemble Techniques to Enhance Wireless Intrusion Detection System In IoT

Rajendran, Viknesh Aditya (2022) Ensemble Techniques to Enhance Wireless Intrusion Detection System In IoT. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (832kB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (731kB) | Preview


The Internet of Things (IoT) is rapidly expanding to have a greater impact on anything from everyday life to enormous industrial activities. The fast expansion of the internet of things has resulted in serious security issues, such as cyber-attacks conducted by incredibly large botnets made up of IoT devices. In order to monitor the network flow on IoT networks intrusion detection systems are very much critical, because they establish a protected traffic condition and safeguards against malicious traffic packets. However, it’s still challenging to detect whether the packet is being malicious or benign and to classify the botnets types, if they are malicious. Most studies are restricted to using IP addresses to categorize just well-known botnets like Mirai, Bashlite etc, But the drawbacks are that the IP addresses can be spoofed. In this research paper, an ensemble model-based intrusion detection system (IDS) was built to determine whether packets are malicious or benign and to categorize botnet types based on md5 hash values. However, evaluation was performed to analyze whether the hash value is dangerous or benign, as well as categorize the kind of botnets and other malware, by integrating the outputs of Light GBM classifier and CatBoost classifier via soft voting classifier. Key metrics such as accuracy, F1-score, Recall and False Alarm Rate were evaluated. 99 percent accuracy has been achieved in classifying whether the packet is benign or malicious and 93 percent accuracy has been attained in classifying the botnet types and the rate of false alarm has been attained to 0.5 percent.

Item Type: Thesis (Masters)
Uncontrolled Keywords: IoT Botnets; LightGbM; CatBoost; Svirtu-AA; Soft Voting classification; Mirai
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software > Computer Security
T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > Computer networks > Internet of things
Divisions: School of Computing > Master of Science in Cyber Security
Depositing User: Tamara Malone
Date Deposited: 29 Dec 2022 14:07
Last Modified: 07 Mar 2023 12:30

Actions (login required)

View Item View Item