Date of Award

Fall 2022

Embargo Period

12-31-2023

Access Type

Dissertation - Open Access

Degree Name

Doctor of Philosophy in Electrical Engineering & Computer Science

Department

Electrical Engineering and Computer Science

Committee Chair

Radu F. Babiceanu

First Committee Member

Laxima Niure Kandel

Second Committee Member

Eduardo A. Rojas Nastrucci

Third Committee Member

Remzi Seker

Fourth Committee Member

Scott Winter

College Dean

James W. Gregory

Abstract

Aviation cybersecurity research has proven to be a complex topic due to the intricate nature of the aviation ecosystem. Over the last two decades, research has been centered on isolated modules of the entire aviation systems, and it has lacked the state-of-the-art tools (e.g. ML/AI methods) that other cybersecurity disciplines have leveraged in their fields. Security research in aviation in the last two decades has mainly focused on: (i) reverse engineering avionics and software certification; (ii) communications due to the rising new technologies of Software Defined Radios (SDRs); (iii) networking cybersecurity concerns such as the inter and intra connections of aircraft within the entire ecosystem.

This dissertation presents an overview of the research in aviation cybersecurity and a ‘Machine Learning and Artificial Intelligence Roadmap’ in which several methods are proposed to allow aviation cybersecurity research to benefit from ML/AI and data science methods: a new threat model to frame the cybersecurity threats and an aviation cybersecurity testbed to perform ML/AI experiments.

Download

Share

COinS