Year
Month
(Peer-Reviewed) Universal Adversarial Examples and Perturbations for Quantum Classifiers
Weiyuan Gong ¹, Dong-Ling Deng 邓东灵 ¹ ²
¹ Center for Quantum Information, IIIS, Tsinghua University, Beijing 100084, People's Republic of China 清华大学 交叉信息研究院 量子信息中心
² Shanghai Qi Zhi Institute, 41th Floor, AI Tower, No. 701 Yunjin Road, Xuhui District, Shanghai 200232, China 上海期智研究院
National Science Review, 2021-07-22
Abstract

Quantum machine learning explores the interplay between machine learning and quantum physics, which may lead to unprecedented perspectives for both fields. In fact, recent works have shown strong evidences that quantum computers could outperform classical computers in solving certain notable machine learning tasks. Yet, quantum learning systems may also suffer from the vulnerability problem: adding a tiny carefully-crafted perturbation to the legitimate input data would cause the systems to make incorrect predictions at a notably high confidence level.

In this paper, we study the universality of adversarial examples and perturbations for quantum classifiers. Through concrete examples involving classifications of real-life images and quantum phases of matter, we show that there exist universal adversarial examples that can fool a set of different quantum classifiers. We prove that for a set of k classifiers with each receiving input data of n qubits, an O(ln k/2ⁿ) increase of the perturbation strength is enough to ensure a moderate universal adversarial risk.

In addition, for a given quantum classifier we show that there exist universal adversarial perturbations, which can be added to different legitimate samples and make them to be adversarial examples for the classifier.

Our results reveal the universality perspective of adversarial attacks for quantum machine learning systems, which would be crucial for practical applications of both near-term and future quantum technologies in solving machine learning problems.
Universal Adversarial Examples and Perturbations for Quantum Classifiers_1
Universal Adversarial Examples and Perturbations for Quantum Classifiers_2
Universal Adversarial Examples and Perturbations for Quantum Classifiers_3
Universal Adversarial Examples and Perturbations for Quantum Classifiers_4
  • Influence of N-doping on dielectric properties of carbon-coated copper nanocomposites in the microwave and terahertz ranges
  • Feirong Huang, Shuting Fan, Yuqi Tian, Xinghao Qu, Xiyang Li, Maofan Qin, Javid Muhammad, Xuefeng Zhang, Zhidong Zhang, Xinglong Dong
  • Journal of Materiomics
  • 2022-11-06
  • Towards integrated mode-division demultiplexing spectrometer by deep learning
  • Ze-huan Zheng, Sheng-ke Zhu, Ying Chen, Huanyang Chen, Jin-hui Chen
  • Opto-Electronic Science
  • 2022-11-01
  • Discovery of novel aspartate derivatives as highly potent and selective FXIa inhibitors
  • Ling Zhang, Wei Chen, Ningning Yao, Shuzeng Hou, Zhiwei Meng, Yi Kong, Chenzhong Liao, Zhouling Xie
  • Journal of Chinese Pharmaceutical Sciences
  • 2022-10-31
  • Switching of K-Q intervalley trions fine structure and their dynamics in n-doped monolayer WS₂
  • Jiajie Pei, Xue Liu, Andrés Granados del Águila, Di Bao, Sheng Liu, Mohamed-Raouf AMARA, Weijie Zhao, Feng Zhang, Congya You, Yongzhe Zhang, Kenji Watanabe, Takashi Taniguchi, Han Zhang, Qihua Xiong
  • Opto-Electronic Advances
  • 2022-10-28
  • Low-loss chip-scale programmable silicon photonic processor
  • Yiwei Xie, Shihan Hong, Hao Yan, Changping Zhang, Long Zhang, Leimeng Zhuang, Daoxin Dai
  • Opto-Electronic Advances
  • 2022-10-28
  • Large-scale and high-quality III-nitride membranes through microcavity-assisted crack propagation by engineering tensile-stressed Ni layers
  • Jung-Hong Min, Kwangjae Lee, Tae-Hoon Chung, Jung-Wook Min, Kuang-Hui L1, Chun Hong Kang, Hoe-Min Kwak, Tae-Hyeon Kim, Youyou Yuan, Kyoung-Kook Kim, Dong-Seon Lee, Tien Khee Ng, Boon S. Ooi
  • Opto-Electronic Science
  • 2022-10-28
  • Metasurface-based nanoprinting: principle, design and advances
  • Rao Fu, Kuixian Chen, Zile Li, Shaohua Yu, Guoxing Zheng
  • Opto-Electronic Science
  • 2022-10-28
  • Table-top optical parametric chirped pulse amplifiers: past and present
  • Audrius Dubietis, Aidas Matijošius
  • Opto-Electronic Advances
  • 2022-09-30
  • ZnO nanowires based degradable high-performance photodetectors for eco-friendly green electronics
  • Bhavani Prasad Yalagala, Abhishek Singh Dahiya, Ravinder Dahiya
  • Opto-Electronic Advances
  • 2022-09-30
  • Crosstalk-free achromatic full Stokes imaging polarimetry metasurface enabled by polarization-dependent phase optimization
  • Yaxin Zhang, Mingbo Pu, Jinjin Jin1, Xinjian Lu, Yinghui Guo, Jixiang Cai, Fei Zhang, Yingli Ha, Qiong He, Mingfeng Xu, Xiong Li, Xiaoliang Ma, Xiangang Luo
  • Opto-Electronic Advances
  • 2022-09-30
  • All-optical logic gate computing for high-speed parallel information processing
  • Shuming Jiao, Junwei Liu, Liwen Zhang, Feihong Yu, Guomeng Zuo, Jingming Zhang, Fang Zhao, Weihao Lin, Liyang Shao
  • Opto-Electronic Science
  • 2022-09-07
  • 100 Hertz frame-rate switching three-dimensional orbital angular momentum multiplexing holography via cross convolution
  • Weijia Meng, Yilin Hua, Ke Cheng, Baoli Li, Tingting Liu, Qinyu Chen, Haitao Luan, Min Gu, Xinyuan Fang
  • Opto-Electronic Science
  • 2022-09-07



  • Non-spreading bessel spatiotemporal optical vortices                                A new finding on the prevalence of rapid water warming during lake ice melting on the Tibetan Plateau
    About
    |
    Contact
    |
    Copyright © PubCard