Predominant Aspects on Security for Quantum Machine Learning: Literature Review

TL;DR

This literature review explores the security challenges and strengths of Quantum Machine Learning, highlighting unique vulnerabilities and mitigation strategies to guide future research and secure deployment.

Contribution

It systematically categorizes security concerns in QML, identifying novel attack vectors and evaluating existing mitigation approaches, serving as a foundational reference.

Findings

QML introduces unique security vulnerabilities not present in classical ML

Mitigation strategies like adversarial training and quantum noise exploitation show promise

Specific risks such as cross-talk and forced operations threaten QML reliability

Abstract

Quantum Machine Learning (QML) has emerged as a promising intersection of quantum computing and classical machine learning, anticipated to drive breakthroughs in computational tasks. This paper discusses the question which security concerns and strengths are connected to QML by means of a systematic literature review. We categorize and review the security of QML models, their vulnerabilities inherent to quantum architectures, and the mitigation strategies proposed. The survey reveals that while QML possesses unique strengths, it also introduces novel attack vectors not seen in classical systems. We point out specific risks, such as cross-talk in superconducting systems and forced repeated shuttle operations in ion-trap systems, which threaten QML's reliability. However, approaches like adversarial training, quantum noise exploitation, and quantum differential privacy have shown potential in enhancing QML robustness. Our review discuss the need for continued and rigorous research to ensure the secure deployment of QML in real-world applications. This work serves as a foundational reference for researchers and practitioners aiming to navigate the security aspects of QML.