NORMA eResearch @NCI Library

Finding IoT privacy issues through malware Detection using XGBoost machine learning technique

Bhardwaj, Parth (2022) Finding IoT privacy issues through malware Detection using XGBoost machine learning technique. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (730kB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (798kB) | Preview


IoT (Internet of Things) has helped in raising the living conditions of people as it has helped in creating a smart environment where all the devices, some that have large significance in the day-to-day life of people, are connected to a single network. The devices connected to the network can be programmed to work according to the needs of the user. These devices can communicate with each other by exchanging data and this will enable the devices in the network to behave in an intelligent manner thereby increasing the comfort of a person living in such an environment. But these environments are highly vulnerable to cyber-attacks which may result in the entire environment collapsing. One major threat to the IoT environments is malware. Malware must be detected in an IoT network for it to be removed. This problem is addressed in the approach proposed here as a malware detection system in IoT environments is proposed here. The malware will be detected using the machine learning based XGBoost classifier. The classifier will be trained separately by using the data in both the IoT-23 and CICIDS-2017 datasets for performing malware detection. The performance of the trained classifier will be evaluated by computing the accuracy and precision and the trained model will be used for creating a desktop application that is able to detect malware in a network based on the network features provided as input. The results of this approach reveal that the XGBoost classifier is effective in detecting malware from an IoT environment and it will also calculate the accuracy and precision between the datasets which are selected for this XGB model. IoT-23 dataset accuracy is more than the CICIDS2017 and the precision is also more in the IoT23.

Item Type: Thesis (Masters)
Moldovan, Arghir-Nicolae
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
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Cyber Security
Depositing User: Tamara Malone
Date Deposited: 28 Apr 2023 13:26
Last Modified: 28 Apr 2023 13:26

Actions (login required)

View Item View Item