中国物理B ›› 2023, Vol. 32 ›› Issue (7): 70304-070304.doi: 10.1088/1674-1056/ac9b32

• • 上一篇    下一篇

A new method of constructing adversarial examples for quantum variational circuits

Jinge Yan(颜金歌)1,2, Lili Yan(闫丽丽)1,2,†, and Shibin Zhang(张仕斌)1,2   

  1. 1 School of Cybersecurity, Chengdu University of Information Technology, Sichuan 610000, China;
    2 Advanced Cryptography and System Security Key Laboratory of Sichuan Province, Sichuan 610000, China
  • 收稿日期:2022-06-27 修回日期:2022-09-24 接受日期:2022-10-19 出版日期:2023-06-15 发布日期:2023-07-05
  • 通讯作者: Lili Yan E-mail:yanlili@cuit.edu.cn
  • 基金资助:
    Project supported by the National Natural Science Foundation of China (Grant Nos. 62076042 and 62102049), the Natural Science Foundation of Sichuan Province (Grant No. 2022NSFSC0535), the Key Research and Development Project of Sichuan Province (Grant Nos. 2021YFSY0012 and 2021YFG0332), the Key Research and Development Project of Chengdu (Grant No. 2021-YF05-02424-GX), and the Innovation Team of Quantum Security Communication of Sichuan Province (Grant No. 17TD0009).

A new method of constructing adversarial examples for quantum variational circuits

Jinge Yan(颜金歌)1,2, Lili Yan(闫丽丽)1,2,†, and Shibin Zhang(张仕斌)1,2   

  1. 1 School of Cybersecurity, Chengdu University of Information Technology, Sichuan 610000, China;
    2 Advanced Cryptography and System Security Key Laboratory of Sichuan Province, Sichuan 610000, China
  • Received:2022-06-27 Revised:2022-09-24 Accepted:2022-10-19 Online:2023-06-15 Published:2023-07-05
  • Contact: Lili Yan E-mail:yanlili@cuit.edu.cn
  • Supported by:
    Project supported by the National Natural Science Foundation of China (Grant Nos. 62076042 and 62102049), the Natural Science Foundation of Sichuan Province (Grant No. 2022NSFSC0535), the Key Research and Development Project of Sichuan Province (Grant Nos. 2021YFSY0012 and 2021YFG0332), the Key Research and Development Project of Chengdu (Grant No. 2021-YF05-02424-GX), and the Innovation Team of Quantum Security Communication of Sichuan Province (Grant No. 17TD0009).

摘要: A quantum variational circuit is a quantum machine learning model similar to a neural network. A crafted adversarial example can lead to incorrect results for the model. Using adversarial examples to train the model will greatly improve its robustness. The existing method is to use automatic differentials or finite difference to obtain a gradient and use it to construct adversarial examples. This paper proposes an innovative method for constructing adversarial examples of quantum variational circuits. In this method, the gradient can be obtained by measuring the expected value of a quantum bit respectively in a series quantum circuit. This method can be used to construct the adversarial examples for a quantum variational circuit classifier. The implementation results prove the effectiveness of the proposed method. Compared with the existing method, our method requires fewer resources and is more efficient.

关键词: quantum variational circuit, adversarial examples, quantum machine learning, quantum circuit

Abstract: A quantum variational circuit is a quantum machine learning model similar to a neural network. A crafted adversarial example can lead to incorrect results for the model. Using adversarial examples to train the model will greatly improve its robustness. The existing method is to use automatic differentials or finite difference to obtain a gradient and use it to construct adversarial examples. This paper proposes an innovative method for constructing adversarial examples of quantum variational circuits. In this method, the gradient can be obtained by measuring the expected value of a quantum bit respectively in a series quantum circuit. This method can be used to construct the adversarial examples for a quantum variational circuit classifier. The implementation results prove the effectiveness of the proposed method. Compared with the existing method, our method requires fewer resources and is more efficient.

Key words: quantum variational circuit, adversarial examples, quantum machine learning, quantum circuit

中图分类号:  (Quantum information)

  • 03.67.-a
03.67.Ac (Quantum algorithms, protocols, and simulations) 03.67.Lx (Quantum computation architectures and implementations)