Date of Award

May 2024

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Computer Science

First Advisor

Hassan Reza

Abstract

With the advances in sensor network technologies, more and more networked things, or smart objects, are being evolved in cyber-physical-based systems including Internet of Things. In recent years, Internet of Things Sensor Networks is a significant subject to a variety of internal and external cyber-attacks, necessitating the development of robust countermeasures tailored to their unique characteristics and limitations. Various prevention and detection techniques have been proposed to mitigate these attacks. Classical security techniques, such as spread spectrum, cryptography, and key management, may not efficiently detect attacks, and can demand sophisticated software and hardware changes, rendering these solutions insufficient to address Internet of Things Sensor Networks security concerns.Machine Learning and Blockchain are considered promising techniques to protect and secure Internet of Things Sensor Networks against cyber-attacks. The ultimate goal of the dissertation is to propose a hybrid security framework of two lines of defense leveraging the strengths of Machine Learning and Blockchain technologies, thereby making Internet of Things Sensor Networks more secure and resilient to cyber-attacks. The first line of defense is attack prevention using Blockchain, while the second line of defense is attack detection using Machine Learning. In case the first line of defense fails to prevent an attack, the second should verify and examine the incoming traffic for any sign of vulnerability, alerting the network to the presence of a malicious attack.

Download

Share

COinS