Real-Time Machine Learning-based Intrusion Detection System (IDS) for Internet of Things (IoT) Networks

The significant growth of Internet of Things devices in different industries has been coupled with a growth in cyberattacks on these devices and their networks. Due to their low storage and processing capacity, Internet of Things devices are unable to support sophisticated Intrusion Detection Systems. Cyber attackers target Internet of Things devices due to their susceptibility to cyberattacks, and they use them as an easy entryway to other systems connected to the same networks. This praxis provides a machine learning-based Intrusion Detection Systems that can detect and classify malicious network traffic in Internet of Things networks in real-time. This Intrusion Detection System is proposed to be implemented on a network-hosted server that monitors network traffic of Internet of Things devices. This praxis uses the BoT-IoT dataset, which contains over 72,000,000 records of real and simulated Internet of Things network traffic. One of the main findings of this research is that the total number of packets per destination Internet Protocol address and record duration are the two features from this dataset that can best classify malicious traffic from normal traffic in Internet of Things networks. The praxis studies three machine learning models: Random Forest, eXtreme Gradient Boosting, and Multilayer Perceptron, a form of an Artificial Neural Network. This research concludes that a machine learning model can be used to accurately detect and classify intrusions in Internet of Things networks in real-time. Out of the three machine learning models investigated, eXtreme Gradient Boosting performs the best with the highest performance metrics and lowest false alarm rate and classification time.

Author

• Alsarhan, Hamza

Language

• en

Keyword

• Internet of Things (IoT)
• Cybersecurity
• IoT Devices
• IoT Networks
• Real-time Intrusion Detection System
• Machine Learning

Date created

• 2023

Type of Work

• Dissertation

License

• All rights reserved

Rights statement

• In Copyright

GW Unit

• Engineering Management

Degree

• D.Engr.

Advisor

• Jones, Michael

Committee Member(s)

• Blackford, Joseph P
• Yassan, Rebecca

Persistent URL

•  https://scholarspace.library.gwu.edu/etd/6h440t30w