Quantum noise protects quantum classifiers against adversaries
Open accessThe DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.
Abstract
Noise in quantum information processing is often viewed as a disruptive and difficult-to-avoid feature, especially in near-term quantum technologies.However, noise has often played beneficial roles, from enhancing weak signals in stochastic resonance to protecting the privacy of data in differential privacy.It is then natural to ask: Can we harness the power of quantum noise that is beneficial to quantum computing?An important current direction for quantum computing is its application to machine learning, such as classification problems.One outstanding problem in machine learning for classification is its sensitivity to adversarial examples.These are small, undetectable perturbations from the original data where the perturbed data is completely misclassified in otherwise extremely accurate classifiers.They can also be considered as worst-case perturbations by unknown noise sources.We show that by taking advantage of depolarization noise in quantum circuits for classification, a robustness bound against adversaries can be derived where the robustness improves with increasing noise.This robustness property is intimately connected with an important security concept called differential privacy, which can be extended to quantum differential privacy.For the protection of quantum data, this quantum protocol can be used against the most general adversaries.Furthermore, we show how the robustness in the classical case can be sensitive to the details of the classification model, but in the quantum case the details of the classification model are absent, thus also providing a potential quantum advantage for classical data.This opens the opportunity to explore other ways in which quantum noise can be used in our favor, as well as identifying other ways quantum algorithms can be helpful in a way which is distinct from quantum speedups.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS
FISHER, R. A. (1936) · Annals of Eugenics · doi:10.1111/j.1469-1809.1936.tb02137.x · Cited by 15,227
Explaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381
Quantum Computing in the NISQ era and beyond
Preskill, J. (2018) · Quantum · doi:10.22331/q-2018-08-06-79 · Cited by 8,830
Quantum Computation and Quantum Information: 10th Anniversary Edition
Nielsen, M. A., & Chuang, I. L. (2012) · doi:10.1017/cbo9780511976667 · Cited by 8,436
Intriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143
Towards Deep Learning Models Resistant to Adversarial Attacks
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2017) · arXiv · doi:10.48550/arxiv.1706.06083 · Cited by 6,602
Gammaitoni, L., Hänggi, P., Jung, P., & Marchesoni, F. (1998) · Reviews of Modern Physics · doi:10.1103/revmodphys.70.223 · Cited by 5,443
Biamonte, J., Wittek, P., Pancotti, N., Rebentrost, P., Wiebe, N., & Lloyd, S. (2017) · Nature · doi:10.1038/nature23474 · Cited by 4,779
Supervised learning with quantum-enhanced feature spaces
Havlíček, V., Córcoles, A. D., Temme, K., Harrow, A. W., Kandala, A., Chow, J. M., & Gambetta, J. M. (2019) · Nature · doi:10.1038/s41586-019-0980-2 · Cited by 2,572
Adversarial machine learning at scale
Kurakin, A., Goodfellow, I., & Bengio, S. (2016) · arXiv · doi:10.48550/arxiv.1611.01236 · Cited by 2,325
Quantum Machine Learning in Feature Hilbert Spaces
Schuld, M., & Killoran, N. (2019) · Physical Review Letters · doi:10.1103/physrevlett.122.040504 · Cited by 1,840 · cited 2×
“The generic form of a quantum kernel classifier [17, 28, 37] is shown in Figure 3.”
Adversarial Examples: Attacks and Defenses for Deep Learning
Yuan, X., He, P., Zhu, Q., & Li, X. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2886017 · Cited by 1,733 · cited 2×
“[43] Xiaoyong Yuan, Pan He, Qile Zhu, and Xiaolin Li.”
Mitarai, K., Negoro, M., Kitagawa, M., & Fujii, K. (2018) · Physical Review A · doi:10.1103/physreva.98.032309 · Cited by 1,639 · cited 3×
“The generic form of a quantum kernel classifier [17, 28, 37] is shown in Figure 3.”
BackgroundMethodError Mitigation for Short-Depth Quantum Circuits
Temme, K., Bravyi, S., & Gambetta, J. M. (2017) · Physical Review Letters · doi:10.1103/physrevlett.119.180509 · Cited by 1,379
Delving into Transferable Adversarial Examples and Black-box Attacks
Liu, Y., Chen, X., Liu, C., & Song, D. (2016) · arXiv · doi:10.48550/arxiv.1611.02770 · Cited by 1,310
Huang, L., Joseph, A. D., Nelson, B., Rubinstein, B. I. P., & Tygar, J. D. (2011) · Proceedings of the 4th ACM workshop on Security and artificial intelligence · doi:10.1145/2046684.2046692 · Cited by 1,194 · cited 1×
“This observation presents an impetus for the vibrant field called adversarial machine learning [18, 21] and this has recently been extended to the quantum domain in adversarial quantum learning [24, 26, 41].”
Foundations of Machine Learning
Mohri, M., Rostamizadeh, A., & Talwalkar, A. (2018) · doi:10.7551/mitpress/10290.001.0001 · Cited by 1,122
Circuit-centric quantum classifiers
Schuld, M., Bocharov, A., Svore, K. M., & Wiebe, N. (2020) · Physical Review A · doi:10.1103/physreva.101.032308 · Cited by 1,057 · cited 2×
“[35] Maria Schuld, Alex Bocharov, Krysta Svore, and Nathan Wiebe.”
BackgroundClassification with Quantum Neural Networks on Near Term Processors
Farhi, E., & Neven, H. (2018) · arXiv · doi:10.48550/arxiv.1802.06002 · Cited by 598
Practical Quantum Error Mitigation for Near-Future Applications
Endo, S., Benjamin, S. C., & Li, Y. (2018) · Physical Review X · doi:10.1103/physrevx.8.031027 · Cited by 562 · cited 2×
“[9] Suguru Endo, Simon C Benjamin, and Ying Li.”
BackgroundA generative modeling approach for benchmarking and training shallow quantum circuits
Benedetti, M., Garcia-Pintos, D., Perdomo, O., Leyton-Ortega, V., Nam, Y., & Perdomo-Ortiz, A. (2019) · npj Quantum Information · doi:10.1038/s41534-019-0157-8 · Cited by 379 · cited 3×
“[3] Marcello Benedetti, Delfina Garcia-Pintos, Oscar Perdomo, Vicente Leyton-Ortega, Yunseong Nam, and Alejandro PerdomoOrtiz.”
Making machine learning robust against adversarial inputs
Goodfellow, I., McDaniel, P., & Papernot, N. (2018) · Communications of the ACM · doi:10.1145/3134599 · Cited by 358
Implementing a distance-based classifier with a quantum interference circuit
Schuld, M., Fingerhuth, M., & Petruccione, F. (2017) · EPL (Europhysics Letters) · doi:10.1209/0295-5075/119/60002 · Cited by 285 · cited 1×
“Then we need to efficiently encode this classical data into quantum states [36].”
Transformation of quantum states using uniformly controlled rotations
Mottonen, M., Vartiainen, J. J., Bergholm, V., & Salomaa, M. M. (2005) · Quantum Information and Computation · doi:10.26421/qic5.6-5 · Cited by 161
Cited by
The Roadmap to 6G Security and Privacy
Porambage, P., Gur, G., Osorio, D. P. M., Liyanage, M., Gurtov, A., & Ylianttila, M. (2021) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2021.3078081 · Cited by 416
Solving nonlinear differential equations with differentiable quantum circuits
Kyriienko, O., Paine, A. E., & Elfving, V. E. (2021) · Physical Review A · doi:10.1103/physreva.103.052416 · Cited by 185
“…by parametrized quantum circuits , also dubbed as quantum neural networks (QNNs) [67], VQAs rapidly expand applications to include classification [72–78], regression [73], generative modelling [79–87], clustering [88, 89], reinforcement learning [90–95], quantum simulation [96–99], quantum…”
BackgroundSolving nonlinear differential equations with differentiable quantum circuits
Kyriienko, O., Paine, A. E., & Elfving, V. E. (2020) · arXiv · doi:10.48550/arxiv.2011.10395 · Cited by 185
Biology and medicine in the landscape of quantum advantages
Cordier, B. A., Sawaya, N. P. D., Guerreschi, G. G., & McWeeney, S. K. (2022) · Journal of The Royal Society Interface · doi:10.1098/rsif.2022.0541 · Cited by 87
“More recently, theoretical work at the intersection of quantum information and differential privacy has been explored [422, 423, 424, 425], with potential applications in the healthcare setting [426].”
BackgroundTowards quantum enhanced adversarial robustness in machine learning
West, M. T., Tsang, S.-L., Low, J. S., Hill, C. D., Leckie, C., Hollenberg, L. C. L., Erfani, S. M., & Usman, M. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00661-1 · Cited by 79
“The pursuit of similar results in the quantum case has already begun, with promising results reported [21, 23].”
BackgroundResultInfluential
Metadata
- Authors
- Du, Y., Hsieh, M.-H., Liu, T., Tao, D., & Liu, N.
- Venue
- Physical Review Research
- Publisher
- American Physical Society (APS)
- Published
- 2021-05-27
- Volume
- 3
- Issue
- 2
- ISSN
- 2643-1564 (ISSN-L)
- OpenAlex
- W3012697779
- Cited by
- 156
- References
- 24
- FWCI
- 7.67
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.