Fetching the paper…

Reading the bibliography…

2020

Robust in Practice: Adversarial Attacks on Quantum Machine Learning

Liao, Haoran, Convy, Ian, Huggins, William J. et al.

Original
PDF
Post on X

Understand

State-of-the-art classical neural networks are observed to be vulnerable to small crafted adversarial perturbations.

A more severe vulnerability has been noted for quantum machine learning (QML) models classifying Haar-random pure states.
This stems from the concentration of measure phenomenon, a property of the metric space when sampled probabilistically, and is independent of the classification protocol.
In order to provide insights into the adversarial robustness of a quantum classifier on real-world classification tasks, we focus on the adversarial robustness in classifying a subset of encoded states that are smoothly generated from a Gaussian latent space.

Robust in Practice: Adversarial Attacks on Quantum Machine Learning · Around

Built on

Zachary Charles, Harrison Rosenberg, and Dimitris Papailiopoulos, “A Geometric Perspective on the Transferability of Adversarial Directions,” in PMLR , Vol. 89 (2018) pp. 1960–1968
Original
1968
Earlier work this paper cites.
Alexander S. Holevo, “On Quasiequivalence of Locally Normal States,” Theoretical and Mathematical Physics 13
1972
Earlier work this paper cites.
Christer Borell, “The Brunn-Minkowski inequality in Gauss space,” Inventiones Mathematicae 30
1975
Earlier work this paper cites.
M. Gromov and V. D. Milman, “A Topological Application of the Isoperimetric Inequality,” American Journal of Mathematics 105
1983
Earlier work this paper cites.
Michel Ledoux, The Concentration of Measure Phenomenon , Mathematical Surveys and Monographs, Vol. 89 (American Mathematical Society, 2001)
2001
Earlier work this paper cites.
Vitali D. Milman, Gideon Schechtman, Asymptotic Theory of Finite Dimensional Normed Spaces: Isoperimetric Inequalities in Riemannian Manifolds , Lecture Notes in Mathematics (Springer, 2002)
2002
Earlier work this paper cites.
Robert Lockhart, “Low-rank Separable States Are A Set of Measure Zero Within the Set of Low-rank States,” Physical Review A 65
2002
Earlier work this paper cites.
Nilesh Dalvi, Pedro Domingos, Mausam, Sumit Sanghai, and Deepak Verma, “Adversarial Classification,” in ACM (2004) p. 99
2004
Earlier work this paper cites.
Roman Orus and Rolf Tarrach, “Weakly-entangled States are Dense and Robust,” Physical Review A 70
2004
Earlier work this paper cites.
Sandu Popescu, Anthony J. Short, and Andreas Winter, “Entanglement and the Foundations of Statistical Mechanics,” Nature Physics 2
2006
Earlier work this paper cites.
Thierry Giordano and Vladimir Pestov, “Some Extremely Amenable Groups Related to Operator Algebras and Ergodic Theory,” Journal of the Institute of Mathematics of Jussieu 6
2007
Earlier work this paper cites.
Vittorio Giovannetti, Seth Lloyd, and Lorenzo Maccone, “Quantum Random Access Memory,” Physical Review Letters 100
2008
Earlier work this paper cites.
Michael A. Nielsen and Isaac L. Chuang, Quantum Computation and Quantum Information (Cambridge University Press, 2010)
2010
Earlier work this paper cites.
Ling Huang, Anthony D. Joseph, Blaine Nelson, Benjamin I.P. Rubinstein, and J. D. Tygar, “Adversarial Machine Learning,” in ACM (2011) pp. 43–57
2011
Earlier work this paper cites.
Markus P. Müller, David Gross, and Jens Eisert, “Concentration of Measure for Quantum States with a Fixed Expectation Value,” Communications in Mathematical Physics 303
2011
Earlier work this paper cites.
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus, “Intriguing Properties of Neural Networks,” in ICLR (2014)
Original
2014
Earlier work this paper cites.
Diederik P. Kingma and Max Welling, “Auto-Encoding Variational Bayes,” in ICLR (2014)
Original
2014
Earlier work this paper cites.
Ian J Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio, “Generative Adversarial Nets,” in NIPS (2014) pp. 2672–2680
2014
Earlier work this paper cites.
Ian J. Goodfellow, Jonathon Shlens, and Christian Szegedy, “Explaining and Harnessing Adversarial Examples,” in ICLR (2015)
Original
2015
Earlier work this paper cites.
Danilo Jimenez Rezende and Shakir Mohamed, “Variational Inference with Normalizing Flows,” in PMLR , Vol. 37 (2015) pp. 1530–1538
2015
Earlier work this paper cites.
Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, and Pascal Frossard, “Robustness of classifiers: from adversarial to random noise,” in NIPS (2016) pp. 1632–1640
Original
2016
Earlier work this paper cites.

Similar

E. Miles Stoudenmire and David J. Schwab, “Supervised Learning with Quantum-Inspired Tensor Networks,” in NIPS (2016) pp. 4799–4807
Original
2016
Cited alongside, same era.
Alec Radford, Luke Metz, and Soumith Chintala, “Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks,” in ICLR (2016)
Original
2016
Cited alongside, same era.
Jacob Biamonte, Peter Wittek, Nicola Pancotti, Patrick Rebentrost, Nathan Wiebe, and Seth Lloyd, “Quantum machine learning,” Nature 549
2017
Cited alongside, same era.
Laurent Dinh, Jascha Sohl-Dickstein, and Samy Bengio, “Density Estimation Using Real NVP,” in ICLR (2017)
Original
2017
Cited alongside, same era.
Martin Arjovsky, Soumith Chintala, and Leon Bottou, “Wasserstein Generative Adversarial Networks,” in PMLR , Vol. 70 (2017) pp. 214–223

Then

Zhengli Zhao, Dheeru Dua, and Sameer Singh, “Generating Natural Adversarial Examples,” in ICLR (2018)
2018
Later among the works it cites.
Saeed Mahloujifar, Dimitrios I. Diochnos, and Mohammad Mahmoody, “The Curse of Concentration in Robust Learning: Evasion and Poisoning Attacks from Concentration of Measure,” in AAAI , Vol. 33 (2019) pp. 4536–4543
2019
Later among the works it cites.
Alexey Kurakin, Ian J. Goodfellow, and Samy Bengio, “Adversarial Examples in the Physical World,” in ICLR (2019)
Original
2019
Later among the works it cites.
Sébastien Bubeck, Eric Price, and Ilya Razenshteyn, “Adversarial Examples from Computational Constraints,” in PMLR , Vol. 97 (2019) pp. 831–840
Original
2019
Later among the works it cites.
Logan Engstrom, Justin Gilmer, Gabriel Goh, Dan Hendrycks, Andrew Ilyas, Aleksander Madry, Reiichiro Nakano, Preetum Nakkiran, Shibani Santurkar, Brandon Tran, Dimitris Tsipras, and Eric Wallace, “Adversarial Examples Are Not Bugs, They Are Features,” in NIPS (2019) pp. 125–136

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Original

2017

Cited alongside, same era.

Alexey Kurakin, Ian J. Goodfellow, and Samy Bengio, “Adversarial Machine Learning at Scale,” in ICLR (2017)

2017

Cited alongside, same era.

Roman Vershynin, “Four lectures on probabilistic methods for data science,” arXiv:1612.06661 (2017)

2017

Cited alongside, same era.

D Spehner, F Illuminati, M Orszag, and W Roga, “Geometric Measures of Quantum Correlations with Bures and Hellinger Distances,” Lectures on General Quantum Correlations and their Applications (2017)

2017

Cited alongside, same era.

John Preskill, “Quantum Computing in the NISQ Era and Beyond,” Quantum 2

2018

Cited alongside, same era.

Anirban Chakraborty, Manaar Alam, Vishal Dey, Anupam Chattopadhyay, and Debdeep Mukhopadhyay, “Adversarial Attacks and Defences: A Survey,” Procedia Computer Science 140

2018

Cited alongside, same era.

Battista Biggio and Fabio Roli, “Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning,” Pattern Recognition 84

2018

Cited alongside, same era.

Justin Gilmer, Luke Metz, Fartash Faghri, Samuel S Schoenholz, Maithra Raghu, Martin Wattenberg, Ian Goodfellow, and Google Brain, “The Relationship Between High-Dimensional Geometry and Adversarial Examples,” arXiv:1801.02774v3 (2018)

2018

Cited alongside, same era.

2019

Later among the works it cites.

William Huggins, Piyush Patil, Bradley Mitchell, K. Birgitta Whaley, and E. Miles Stoudenmire, “Towards Quantum Machine Learning with Tensor Networks,” Quantum Science and Technology 4

2019

Later among the works it cites.

Marcello Benedetti, Erika Lloyd, Stefan Sack, and Mattia Fiorentini, “Parameterized Quantum Circuits as Machine Learning Models,” Quantum Science and Technology 4

2019

Later among the works it cites.

Ajil Jalal, Andrew Ilyas, and Constantinos Daskalakis, “The Robust Manifold Defense: Adversarial Training using Generative Models,” arXiv: 1712.09196v5 (2019)

2019

Later among the works it cites.

Jens Behrmann, Will Grathwohl, Ricky T. Q. Chen, David Duvenaud, and Jörn-Henrik Jacobsen, “Invertible Residual Networks,” in PMLR , Vol. 97 (2019) pp. 573–582

2019

Later among the works it cites.

Han Zhang, Ian Goodfellow, Dimitris Metaxas, and Augustus Odena, “Self-Attention Generative Adversarial Networks,” in PMLR , Vol. 97 (2019) pp. 7354–7363

2019

Later among the works it cites.

Patrick J. Coles, M. Cerezo, and Lukasz Cincio, “Strong bound between trace distance and Hilbert-Schmidt distance for low-rank states,” Physical Review A 100

2019

Later among the works it cites.

Yi Xia, Wei Li, Quntao Zhuang, and Zheshen Zhang, “Quantum-enhanced Data Classification with a Variational Entangled Sensor Network,” arXiv: 2006.11962 (2020)

2020

Closest in time.

Nana Liu and Peter Wittek, “Vulnerability of Quantum Classification to Adversarial Perturbations,” Physical Review A 101

2020

Closest in time.

Sirui Lu, Lu-Ming Duan, and Dong-Ling Deng, “Quantum Adversarial Machine Learning,” Physical Review Research 2

2020

Closest in time.

Yuxuan Du, Min-Hsiu Hsieh, Tongliang Liu, Dacheng Tao, and Nana Liu, “Quantum Noise Protects Quantum Classifiers Against Adversaries,” arXiv: 2003.09416 (2020)

2020

Closest in time.

Ji Guan, Wang Fang, and Mingsheng Ying, “Robustness Verification of Quantum Machine Learning,” arXiv:2008.07230 (2020)

2020

Closest in time.

Jan Philip Göpfert, André Artelt, Heiko Wersing, and Barbara Hammer, “Adversarial Attacks Hidden in Plain Sight,” Advances in Intelligent Data Analysis (2020)

2020

Closest in time.

Shuxiang Cao, Leonard Wossnig, Brian Vlastakis, Peter Leek, and Edward Grant, “Cost-function Embedding and Dataset Encoding for Machine Learning with Parameterized Quantum Circuits,” Physical Review A 101

2020

Closest in time.

John Martyn, Guifre Vidal, Chase Roberts, and Stefan Leichenauer, “Entanglement and Tensor Networks for Supervised Image Classification,” arXiv:2007.06082 (2020)

2020

Closest in time.

Ryan Larose and Brian Coyle, “Robust Data Encodings for Quantum Classifiers,” Physical Review A 102

2020

Closest in time.