Detection of Physiological Data Tampering Attacks with Quantum Machine Learning

TL;DR

This study evaluates the effectiveness of Quantum Machine Learning in detecting physiological data tampering attacks, showing it outperforms classical models in certain attack types but struggles with subtle adversarial perturbations.

Contribution

It is the first comparison of QML and classical ML for detecting physiological data tampering, highlighting QML's strengths and limitations in this domain.

Findings

QML models achieve 75%-95% accuracy in label-flipping attack detection.

Both QML and classical models struggle with subtle adversarial perturbations.

QML outperforms classical algorithms in some cases of complex attack detection.

Abstract

The widespread use of cloud-based medical devices and wearable sensors has made physiological data susceptible to tampering. These attacks can compromise the reliability of healthcare systems which can be critical and life-threatening. Detection of such data tampering is of immediate need. Machine learning has been used to detect anomalies in datasets but the performance of Quantum Machine Learning (QML) is still yet to be evaluated for physiological sensor data. Thus, our study compares the effectiveness of QML for detecting physiological data tampering, focusing on two types of white-box attacks: data poisoning and adversarial perturbation. The results show that QML models are better at identifying label-flipping attacks, achieving accuracy rates of 75%-95% depending on the data and attack severity. This superior performance is due to the ability of quantum algorithms to handle complex and high-dimensional data. However, both QML and classical models struggle to detect more sophisticated adversarial perturbation attacks, which subtly alter data without changing its statistical properties. Although QML performed poorly against this attack with around 45%-65% accuracy, it still outperformed classical algorithms in some cases.