Quantum computing promises to enhance machine learning and artificial intelligence. Different quantum algorithms have been proposed to improve a wide spectrum of machine learning tasks. Yet, recent theoretical works show that, similar to traditional classifiers based on deep classical neural networks, quantum classifiers would suffer from the vulnerability problem: adding tiny carefully-crafted perturbations to the legitimate original data samples would facilitate incorrect predictions at a notably high confidence level. This will pose serious problems for future quantum machine learning applications in safety and security-critical scenarios. Here, we report the first experimental demonstration of quantum adversarial learning with programmable superconducting qubits. We train quantum classifiers, which are built upon variational quantum circuits consisting of ten transmon qubits featuring average lifetimes of 150 $\mu$s, and average fidelities of simultaneous single- and two-qubit gates above 99.94% and 99.4% respectively, with both real-life images (e.g., medical magnetic resonance imaging scans) and quantum data. We demonstrate that these well-trained classifiers (with testing accuracy up to 99%) can be practically deceived by small adversarial perturbations, whereas an adversarial training process would significantly enhance their robustness to such perturbations. Our results reveal experimentally a crucial vulnerability aspect of quantum learning systems under adversarial scenarios and demonstrate an effective defense strategy against adversarial attacks, which provide a valuable guide for quantum artificial intelligence applications with both near-term and future quantum devices.

中文翻译：

---

具有可编程超导量子位的实验性量子对抗学习

量子计算有望增强机器学习和人工智能。已经提出了不同的量子算法来改进广泛的机器学习任务。然而，最近的理论工作表明，与基于深度经典神经网络的传统分类器类似，量子分类器会受到漏洞问题的困扰：在合法的原始数据样本中添加精心设计的微小扰动会在非常高的置信度下促进错误预测. 这将为未来的量子机器学习应用在安全和安全关键场景中带来严重问题。在这里，我们报告了使用可编程超导量子位进行量子对抗学习的首次实验演示。我们训练量子分类器，它们建立在由十个传输量子比特组成的变分量子电路上，平均寿命为 150 美元/亩，同时单量子比特和双量子比特门的平均保真度分别高于 99.94% 和 99.4%，两张真实图像（例如，医学磁共振成像扫描）和量子数据。我们证明了这些训练有素的分类器（测试准确率高达 99%）实际上可以被小的对抗性扰动所欺骗，而对抗性训练过程将显着提高它们对这种扰动的鲁棒性。我们的结果通过实验揭示了对抗性场景下量子学习系统的一个关键漏洞方面，并展示了一种针对对抗性攻击的有效防御策略，