This dissertation is about a particular style of research. The philosophy of this style is that in order to scientifically understand deep learning, it is fruitful to investigate what happens when neural networks are trained on simple, mathematically well-defined tasks. Even though the training data is simple, the training algorithm can end up…

Machine learning (ML) techniques have been successfully applied to a wide array of applications. This dissertation aims to take application data handling into account when developing ML-based solutions for real-world problems through a holistic framework. To demonstrate the generality of our framework, we consider two real-world applications: spam…

Digital systems are pervasive in modern societies -- augmenting personal and commercial driving, detecting cancer, and exploiting transitory events in financial markets. Attacks on these systems are growing in number, sophistication, and impact. Current cyber defenses are proving inadequate against some of these attacks. Cyber defense tools that…

Cyberattacks pose a significant threat to university institutions as universities increasingly rely on computer networks to conduct day-to-day business activities. University information technology (IT) leaders are concerned about the increasing level of cyberattacks because these attacks can result in the loss of sensitive data, identity theft,…

The increasing complexity of modern power systems, coupled with the integration of diverse rapidly evolving technologies involving physical systems requiring cybersecurity, has presented significant challenges for engineers in the field and researchers in laboratory facilities. This research and dissertation presents the development of a…