Date of Award

May 2021

Document Type


Degree Name

Doctor of Philosophy (PhD)


Civil Engineering

Committee Member

Mashrur Chowdhury

Committee Member

Amy Apon

Committee Member

Feng Luo

Committee Member

Long Cheng


The transportation system is rapidly evolving with new connected and automated vehicle (CAV) technologies that integrate CAVs with other vehicles and roadside infrastructure to form a transportation cyber-physical system (TCPS). Through connectivity, CAVs affect their environments and vice versa, increasing the size of the cyberattack surface and the risk of exploitation of security vulnerabilities by malicious actors. Thus, a greater understanding of potential CAV-TCPS cyber-attacks and of ways to prevent them is a high priority. Moreover, making the CAV navigate safely in an unexpected environment is a critical safety requirement. Considering the safety while maintaining the in-vehicle security is the focus of this study, where first, in part 1, the author explores the CAV safety through machine learning models, more specifically deep neural network, to help the vehicle to navigate safely in an unexpected environment, which is required for real-world deployment and has not been fully explored by researchers and industries. In part 2, the author developed a connected vehicle application development platform (CVDeP), such that developers can develop and validate the CAV safety and mobility applications in a controlled and real-world connected vehicle testbed. Our study shows that applications developed through the platform meet the safety requirements of connected vehicle applications. Later, in part 3, the author explores the in-vehicle security aspect, where the author leverages the state-of-the-art cloud supported quantum computers to classify in-vehicle cyberattacks, more specifically amplitude shift attacks. The author develop the quantum-classical hybrid neural network to detect amplitude shift in-vehicle cyberattack. This study integrates the digital infrastructure and a CAV’s in-vehicle system, where the author has shown the potential of using a combination of quantum and classical neural network to improve the cyberattack detection accuracy compared to classical neural network and quantum neural network alone.



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.