Experimental robustness benchmark of quantum neural network on a superconducting quantum processor
This work addresses the vulnerability of quantum machine learning models to adversarial attacks, establishing a critical experimental framework for secure QML deployment, though it is incremental in extending classical robustness concepts to quantum systems.
The authors conducted the first systematic experimental robustness benchmark for 20-qubit quantum neural network classifiers on a superconducting processor, finding that adversarial training reduces sensitivity to perturbations and that QNNs show superior robustness compared to classical networks due to quantum noise, with empirical bounds deviating minimally (3×10⁻³) from theoretical limits.
Quantum machine learning (QML) models, like their classical counterparts, are vulnerable to adversarial attacks, hindering their secure deployment. Here, we report the first systematic experimental robustness benchmark for 20-qubit quantum neural network (QNN) classifiers executed on a superconducting processor. Our benchmarking framework features an efficient adversarial attack algorithm designed for QNNs, enabling quantitative characterization of adversarial robustness and robustness bounds. From our analysis, we verify that adversarial training reduces sensitivity to targeted perturbations by regularizing input gradients, significantly enhancing QNN's robustness. Additionally, our analysis reveals that QNNs exhibit superior adversarial robustness compared to classical neural networks, an advantage attributed to inherent quantum noise. Furthermore, the empirical upper bound extracted from our attack experiments shows a minimal deviation ($3 \times 10^{-3}$) from the theoretical lower bound, providing strong experimental confirmation of the attack's effectiveness and the tightness of fidelity-based robustness bounds. This work establishes a critical experimental framework for assessing and improving quantum adversarial robustness, paving the way for secure and reliable QML applications.