Zhang Huili, Jiang Si, Wang Xin, Zhang Wengang, Huang Xianzhi, Ouyang Xiaolong, Yu Yefei, Liu Yanqing, Deng Dong-Ling, Duan L-M
Center for Quantum Information, IIIS, Tsinghua University, Beijing, 100084, P. R. China.
School of JiaYang, Zhejiang Shuren University, Hangzhou, 310015, P. R. China.
Nat Commun. 2022 Aug 25;13(1):4993. doi: 10.1038/s41467-022-32611-7.
Classification and identification of different phases and the transitions between them is a central task in condensed matter physics. Machine learning, which has achieved dramatic success in a wide range of applications, holds the promise to bring unprecedented perspectives for this challenging task. However, despite the exciting progress made along this direction, the reliability of machine-learning approaches in experimental settings demands further investigation. Here, with the nitrogen-vacancy center platform, we report a proof-of-principle experimental demonstration of adversarial examples in learning topological phases. We show that the experimental noises are more likely to act as adversarial perturbations when a larger percentage of the input data are dropped or unavailable for the neural network-based classifiers. We experimentally implement adversarial examples which can deceive the phase classifier with a high confidence, while keeping the topological properties of the simulated Hopf insulators unchanged. Our results explicitly showcase the crucial vulnerability aspect of applying machine learning techniques in experiments to classify phases of matter, which can benefit future studies in this interdisciplinary field.
不同相的分类、识别以及它们之间的转变是凝聚态物理中的核心任务。机器学习在广泛的应用中取得了巨大成功，有望为这项具有挑战性的任务带来前所未有的视角。然而，尽管在这个方向上取得了令人兴奋的进展，但机器学习方法在实验环境中的可靠性仍需进一步研究。在此，我们利用氮空位中心平台，报告了在学习拓扑相过程中对抗性示例的原理验证实验演示。我们表明，当基于神经网络的分类器有更大比例的输入数据被丢弃或不可用时，实验噪声更有可能充当对抗性扰动。我们通过实验实现了能够以高置信度欺骗相分类器的对抗性示例，同时保持模拟霍普夫绝缘体的拓扑性质不变。我们的结果明确展示了在实验中应用机器学习技术来对物质相进行分类时关键的脆弱性方面，这将有益于这个跨学科领域的未来研究。
