Quantum Machine Learning: Performance and Security Implications in Real-World Applications

TL;DR

The work addresses security and performance implications of quantum machine learning (QML) in real-world contexts. It benchmarks QSVM, VQA, and QCNN against classical SVM and MLP on an Alzheimer's dataset, highlighting the distinct quantum architectures: kernel-based, variational, and convolutional approaches. Findings indicate that, in simulated environments, QML generally does not surpass classical methods in learning performance and incurs substantial computational overhead, with QCNN sometimes matching but not exceeding classical accuracy. The study also discusses inherited classical vulnerabilities and new quantum-specific attack vectors (e.g., exploiting quantum noise), underscoring the need for hardware advances and robust security defenses before widescale deployment in sensitive domains.

Abstract

Quantum computing has garnered significant attention in recent years from both academia and industry due to its potential to achieve a "quantum advantage" over classical computers. The advent of quantum computing introduces new challenges for security and privacy. This poster explores the performance and security implications of quantum computing through a case study of machine learning in a real-world application. We compare the performance of quantum machine learning (QML) algorithms to their classical counterparts using the Alzheimer's disease dataset. Our results indicate that QML algorithms show promising potential while they still have not surpassed classical algorithms in terms of learning capability and convergence difficulty, and running quantum algorithms through simulations on classical computers requires significantly large memory space and CPU time. Our study also indicates that QMLs have inherited vulnerabilities from classical machine learning algorithms while also introduce new attack vectors.