Quantum Properties Trojans (QuPTs) for Attacking Quantum Neural Networks

TL;DR

This paper introduces Quantum Properties Trojans (QuPTs), a novel stealthy attack method exploiting quantum gate properties to compromise quantum neural networks, significantly reducing their accuracy.

Contribution

It presents the first Trojan attack specifically designed for fully quantum neural networks, utilizing quantum gate properties to insert stealthy malicious effects.

Findings

QuPTs significantly impact QNN performance, reducing accuracy by up to 23%.

QuPTs are more stealthy compared to previous attack methods.

First demonstration of Trojan attacks on fully quantum neural networks.

Abstract

Quantum neural networks (QNN) hold immense potential for the future of quantum machine learning (QML). However, QNN security and robustness remain largely unexplored. In this work, we proposed novel Trojan attacks based on the quantum computing properties in a QNN-based binary classifier. Our proposed Quantum Properties Trojans (QuPTs) are based on the unitary property of quantum gates to insert noise and Hadamard gates to enable superposition to develop Trojans and attack QNNs. We showed that the proposed QuPTs are significantly stealthier and heavily impact the quantum circuits' performance, specifically QNNs. The most impactful QuPT caused a deterioration of 23% accuracy of the compromised QNN under the experimental setup. To the best of our knowledge, this is the first work on the Trojan attack on a fully quantum neural network independent of any hybrid classical-quantum architecture.