Fundamentals of Quantum Machine Learning and Robustness

TL;DR

This paper introduces the fundamentals of quantum machine learning, emphasizing the importance of robustness against adversarial inputs and connecting quantum principles with classical adversarial perspectives.

Contribution

It establishes a shared conceptual foundation for QML and explores the impact of quantum principles on adversarial robustness, bridging theory and physical quantum properties.

Findings

Highlights the influence of superposition, entanglement, and measurement on robustness.

Connects adversarial perspectives from classical and quantum computing.

Motivates study of QML robustness in adversarial settings.

Abstract

Quantum machine learning (QML) sits at the intersection of quantum computing and classical machine learning, offering the prospect of new computational paradigms and advantages for processing complex data. This chapter introduces the fundamentals of QML for readers from both communities, establishing a shared conceptual foundation. We connect the worst-case, adversarial perspective from theoretical computer science with the physical principles of quantum systems, highlighting how superposition, entanglement, and measurement collapse influence learning and robustness. Special attention is given to adversarial robustness, understood as the ability of QML models to resist inputs designed to cause failure. We motivate the study of QML in adversarial settings, outlining distinctions between classical and quantum data and computations when the adversary is a core element. This chapter serves as a starting point to adversarial and robust quantum machine learning in subsequent chapters.