Scholarlink

<p>Quantum machine learning (QML) models, like their classical counterparts, are intrinsically vulnerable to adversarial attacks, hindering their secure deployment. Here, we report the first systematic experimental benchmark of robustness for 20-qubit quantum neural network (QNN) classifiers executed on a superconducting processor. Our benchmarking protocol features an efficient adversarial attack algorithm tailored for quantum hardware, enabling the diagnosis of QNN’s robustness across diverse datasets. The empirical upper bound extracted from our attack experiments deviates by only 3 × 10<sup>−3</sup> from the analytical lower bound, providing strong experimental confirmation of our attack’s precision and the tightness of the fidelity-based robustness bounds. Furthermore, our quantitative analysis reveals that adversarial training mitigates sensitivity to targeted perturbations by regularizing input gradients, thereby significantly enhancing QNN robustness. Additionally, we observe that experimentally measured QNNs exhibit higher adversarial robustness than classical neural networks, an effect attributed to inherent quantum noise. Our work establishes the first scalable and experimentally accessible framework for robustness benchmarking, paving the way for secure and reliable QML applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Experimental robustness benchmarking of quantum neural networks on a superconducting quantum processor

  • 期刊论文

  • 发表日期：

    2026年4月27日

查看全文
  • Hai-Feng Zhang,
  • Zhao-Yun Chen,
  • Peng Wang,
  • Liang-Liang Guo,
  • Tian-Le Wang,
  • Xiao-Yan Yang,
  • Ren-Ze Zhao,
  • Ze-An Zhao,
  • Sheng Zhang,
  • Lei Du,
  • Hao-Ran Tao,
  • Zhi-Long Jia,
  • Wei-Cheng Kong,
  • Huan-Yu Liu,
  • Athanasios V. Vasilakos,
  • Yang Yang,
  • Yu-Chun Wu,
  • Ji Guan,
  • Peng Duan,
  • Guo-Ping Guo

摘要

Quantum machine learning (QML) models, like their classical counterparts, are intrinsically vulnerable to adversarial attacks, hindering their secure deployment. Here, we report the first systematic experimental benchmark of robustness for 20-qubit quantum neural network (QNN) classifiers executed on a superconducting processor. Our benchmarking protocol features an efficient adversarial attack algorithm tailored for quantum hardware, enabling the diagnosis of QNN’s robustness across diverse datasets. The empirical upper bound extracted from our attack experiments deviates by only 3 × 10−3 from the analytical lower bound, providing strong experimental confirmation of our attack’s precision and the tightness of the fidelity-based robustness bounds. Furthermore, our quantitative analysis reveals that adversarial training mitigates sensitivity to targeted perturbations by regularizing input gradients, thereby significantly enhancing QNN robustness. Additionally, we observe that experimentally measured QNNs exhibit higher adversarial robustness than classical neural networks, an effect attributed to inherent quantum noise. Our work establishes the first scalable and experimentally accessible framework for robustness benchmarking, paving the way for secure and reliable QML applications.