QSentry: Backdoor Detection for Quantum Neural Networks via Measurement Clustering

TL;DR

QSentry is a novel quantum backdoor detection framework that uses measurement clustering to identify anomalies in quantum neural networks, significantly improving detection accuracy and robustness against poisoning attacks.

Contribution

The paper introduces QSentry, a new quantum backdoor detection method employing measurement clustering to identify statistical anomalies in QNN outputs.

Findings

Achieves up to 93.2% F1 score at 10% poisoning rate.

Effectively detects backdoors with high accuracy across various attack scenarios.

Outperforms three state-of-the-art detection methods.

Abstract

Quantum neural networks (QNNs) are an important model for implementing quantum machine learning (QML), while they demonstrate a high degree of vulnerability to backdoor attacks similar to classical networks. To address this issue, a quantum backdoor attack detection framework called QSentry is proposed, in which a quantum Measurement Clustering method is introduced to detect backdoors by identifying statistical anomalies in measurement outputs. It is demonstrated that QSentry can effectively detect anomalous distributions induced by backdoor samples with extensive experiments. It achieves a 75.8% F1 score even under a 1% poisoning rate, and further improves to 85.7% and 93.2% as the poisoning rate increases to 5% and 10%, respectively. The integration of silhouette coefficients and relative cluster size enable QSentry to precisely isolate backdoor samples, yielding estimates that closely match actual poisoning ratios. Evaluations under various quantum attack scenarios demonstrate that QSentry delivers superior robustness and accuracy compared with three state-of-the-art detection methods. This work establishes a practical and effective framework for mitigating backdoor threats in QML.