Quantum Adversarial Machine Learning: Status, Challenges and Perspectives

Quantum adversarial machine learning Is regarded as a promising approach for studying vulnerabilities of machine learning approaches in adversarial settings and developing defense solutions for adversarial inputs and manipulations in quantum systems. In this paper, we present a current status, proposed approaches and challenges in quantum adversarial machine learning by concentrating on the problems and proposed solutions. We also outline the anticipated problems and perspectives for quantum-assisted machine learning in Near-term quantum computers and limitation in datasets, applications and adversarial examples. With this article, we hope that the readers can have a more thorough understanding of quantum adversarial machine learning and the research trends in this area.

[1]  Danda B. Rawat,et al.  Study of Adversarial Machine Learning with Infrared Examples for Surveillance Applications , 2020 .

[2]  Shouvanik Chakrabarti,et al.  Quantum Wasserstein Generative Adversarial Networks , 2019, NeurIPS.

[3]  Tad Hogg,et al.  Quantum-assisted associative adversarial network: applying quantum annealing in deep learning , 2019, Quantum Machine Intelligence.

[4]  Thierry Paul,et al.  Quantum computation and quantum information , 2007, Mathematical Structures in Computer Science.

[5]  Hartmut Neven,et al.  Classification with Quantum Neural Networks on Near Term Processors , 2018, 1802.06002.

[6]  Simone Severini,et al.  Hierarchical quantum classifiers , 2018, npj Quantum Information.

[7]  Maria Schuld,et al.  Quantum Machine Learning in Feature Hilbert Spaces. , 2018, Physical review letters.

[8]  Tobias J. Osborne,et al.  Training deep quantum neural networks , 2020, Nature Communications.

[9]  Soonwon Choi,et al.  Quantum convolutional neural networks , 2018, Nature Physics.

[10]  LiChenliang,et al.  Adversarial Attacks on Deep-learning Models in Natural Language Processing , 2020 .

[11]  Kristan Temme,et al.  Supervised learning with quantum-enhanced feature spaces , 2018, Nature.

[12]  Qiang Xu,et al.  Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networks , 2018, AAAI.

[13]  Stefan Woerner,et al.  Quantum Generative Adversarial Networks for learning and loading random distributions , 2019, npj Quantum Information.

[14]  Sirui Lu,et al.  Quantum Adversarial Machine Learning , 2020, ArXiv.

[15]  YaoChong Li,et al.  A quantum deep convolutional neural network for image recognition , 2020, Quantum Science and Technology.

[16]  M. Schuld,et al.  Circuit-centric quantum classifiers , 2018, Physical Review A.

[17]  Ekert,et al.  Quantum cryptography based on Bell's theorem. , 1991, Physical review letters.

[18]  E. Torrontegui,et al.  Unitary quantum perceptron as efficient universal approximator , 2018, EPL (Europhysics Letters).

[19]  Seth Lloyd,et al.  Quantum embeddings for machine learning , 2020 .

[20]  Iordanis Kerenidis,et al.  Quantum Algorithms for Deep Convolutional Neural Networks , 2020, ICLR.

[21]  P. Wittek,et al.  Vulnerability of quantum classification to adversarial perturbations , 2019, Physical Review A.

[22]  John Preskill,et al.  Quantum Computing in the NISQ era and beyond , 2018, Quantum.

[23]  Keisuke Fujii,et al.  Quantum circuit learning , 2018, Physical Review A.

[24]  Jerzy Dajka,et al.  Distance between quantum states in the presence of initial qubit-environment correlations: A comparative study , 2011, 1107.1732.

[25]  Seth Lloyd,et al.  Continuous-variable quantum neural networks , 2018, Physical Review Research.

[26]  Shu-Hao Wu,et al.  Quantum generative adversarial learning in a superconducting quantum circuit , 2018, Science Advances.

[27]  P. A. M. Casares,et al.  A quantum active learning algorithm for sampling against adversarial attacks , 2019, New Journal of Physics.

[28]  Pan He,et al.  Adversarial Examples: Attacks and Defenses for Deep Learning , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[29]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[30]  S. Lloyd,et al.  Quantum algorithms for supervised and unsupervised machine learning , 2013, 1307.0411.

[31]  Tongliang Liu,et al.  Quantum noise protects quantum classifiers against adversaries , 2020, ArXiv.

[32]  Dmytro Bondarenko,et al.  Quantum Autoencoders to Denoise Quantum Data. , 2020, Physical review letters.

[33]  J. Cirac,et al.  Goals and opportunities in quantum simulation , 2012, Nature Physics.

[34]  Seth Lloyd,et al.  Quantum Generative Adversarial Learning. , 2018, Physical review letters.

[35]  David A. Wagner,et al.  Audio Adversarial Examples: Targeted Attacks on Speech-to-Text , 2018, 2018 IEEE Security and Privacy Workshops (SPW).

[36]  Tom Goldstein,et al.  Are adversarial examples inevitable? , 2018, ICLR.

[37]  Rupak Biswas,et al.  Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers , 2017, Quantum Science and Technology.

[38]  Elvis Dohmatob,et al.  Generalized No Free Lunch Theorem for Adversarial Robustness , 2018, ICML.

[39]  Alan Aspuru-Guzik,et al.  Variational Quantum Generators: Generative Adversarial Quantum Machine Learning for Continuous Distributions , 2019, Advanced Quantum Technologies.

[40]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[41]  Dirk Englund,et al.  Quantum optical neural networks , 2018, npj Quantum Information.