CoChat
Sign Up
Cited by 79Quantum Computing Algorithms and ArchitectureAdversarial Robustness in Machine LearningQuantum Information and Cryptography

Towards quantum enhanced adversarial robustness in machine learning

Open access
West, Maxwell T., Tsang, Shu-Lok, Low, Jia S., Hill, Charles D., Leckie, Christopher, Hollenberg, Lloyd C. L., Erfani, Sarah M., Usman, Muhammad·2023·Nature Machine Intelligence
DOI 10.1038/s42256-023-00661-1
Open this paper in CoChat — free accountOpen PDF

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s42256-023-00661-1

Cites

14 of 14 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The QT-CNN enhances robustness against adversarial inputs.

    “Our approach employs a hybrid quantum-classical training mechanism, where quantum circuits are utilized to optimize the weight parameters of the CNN, thus enhancing its performance and robustness against adversarial inputs [19].”

    From Quantum-Trained Convolutional Neural Network for Deepfake Audio Detection (2025) · cites this paper as [19]

    The ARCHITECTURE section (page unavailable) discusses hybrid models that pass data through quantum filters before a classical CNN and says they may inherit adversarial-robustness guarantees. It presents that robustness as a possibility and an open question, not as a demonstrated improvement in a QT-CNN; it also does not say quantum circuits optimize CNN weights. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 52

  1. Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013). · arXiv
  2. Huang, L., Joseph, A. D., Nelson, B., Rubinstein, B. I. & Tygar, J. D. Adversarial machine learning. In Proceedings of the 4th ACM Workshop on Security and Artificial Intelli- gence, AISec '11, 43-58 (Association for Computing Machin- ery, New York, NY, USA, 2011).
  3. Su, J., Vargas, D. V. & Sakurai, K. One pixel attack for fooling deep neural networks. IEEE Transactions on Evolu- tionary Computation 23, 828-841 (2019).
  4. Athalye, A., Carlini, N. & Wagner, D. Obfuscated gradients give a false sense of security: Circumventing defenses to ad- versarial examples. In International Conference on Machine Learning, 274-283 (PMLR, 2018).
  5. Eykholt, K., Evtimov, I., Fernandes, E., Li, B., Rahmati, A., Xiao, C., Prakash, A., Kohno, T., & Song, D. Robust physical-world attacks on deep learning visual classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1625-1634 (2018).
  6. Carlini, N. & Wagner, D. Adversarial examples are not easily detected: Bypassing ten detection methods. In Proceedings of the 10th ACM Workshop on Artificial Intelligence and Se- curity, 3-14 (2017).
  7. Wong, E., Rice, L. & Kolter, J. Z. Fast is better than free: Re- visiting adversarial training. CoRR abs/2001.03994 (2020). 2001.03994. · arXiv
  8. Goodfellow, I., McDaniel, P. & Papernot, N. Making machine learning robust against adversarial inputs. Commun. ACM 61, 56-66 (2018).
  9. Miller, D. J., Xiang, Z. & Kesidis, G. Adversarial learning targeting deep neural network classification: A comprehen- sive review of defenses against attacks. Proceedings of the IEEE 108, 402-433 (2020).
  10. Ilyas, A., Santurkar, S., Tsipras, D., Engstrom, L., Tran, B. & Madry, A. Adversarial examples are not bugs, they are features. Advances in Neural Information Processing Systems 32 (2019).
  11. Sharif, M., Bhagavatula, S., Bauer, L. & Reiter, M. K. Acces- sorize to a crime: Real and stealthy attacks on state-of-the- art face recognition. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, CCS '16, 1528-1540 (Association for Computing Machinery, New York, NY, USA, 2016).
  12. Lu, S., Duan, L.-M. & Deng, D.-L. Quantum adversarial ma- chine learning. Physical Review Research 2, 033212 (2020).
  13. Liu, N. & Wittek, P. Vulnerability of quantum classifica- tion to adversarial perturbations. Phys. Rev. A 101, 062331 (2020).
  14. Du, Y., Hsieh, M.-H., Liu, T., Tao, D. & Liu, N. Quantum noise protects quantum classifiers against adversaries. Phys- ical Review Research 3, 023153 (2021).
  15. Guan, J., Fang, W. & Ying, M. Robustness verification of quantum classifiers. In International Conference on Com- puter Aided Verification, 151-174 (Springer, 2021).
  16. Ren, W. et al. Experimental quantum adversarial learning with programmable superconducting qubits. Nature Compu- tational Science 2, 711 (2022).
  17. Liao, H., Convy, I., Huggins, W. J. & Whaley, K. B. Ro- bust in practice: Adversarial attacks on quantum machine learning. Physical Review A 103, 042427 (2021).
  18. Kehoe, A., Wittek, P., Xue, Y. & Pozas-Kerstjens, A. De- fence against adversarial attacks using classical and quantum- enhanced boltzmann machines. Machine Learning: Science and Technology 2, 045006 (2021).
  19. West, M., Erfani, S.M., Leckie, C., Sevior, M., Hollenberg, L.C.L., Usman, M. Benchmarking adversarially robust quan- tum machine learning at scale. arXiv:2211.12681 (2022). · arXiv
  20. Lecun, Y., Bottou, L., Bengio, Y. & Haffner, P. Gradient- based learning applied to document recognition. Proceedings of the IEEE 86, 2278-2324 (1998).
  21. Dallaire-Demers, P.-L. & Killoran, N. Quantum generative adversarial networks. Physical Review A 98, 012324 (2018).
  22. Banchi, L., Pereira, J., & Pirandola, S. Generalization in Quantum Machine Learning: A Quantum Information Stand- point. PRX Quantum 2, 040321 (2021).
  23. Gong, W. & Deng, D. Universal adversarial examples and perturbations for quantum classifiers. National Science Re- view 9, 6 (2022)
  24. LaRose, R. & Coyle, B. Robust data encodings for quantum classifiers. Physical Review A 102, 032420 (2020).
  25. Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., & Bharath, A. A. Generative adversarial net- works: An overview. IEEE Signal Processing Magazine 35, 53-65 (2018).
  26. Chen, P.-Y., Zhang, H., Sharma, Y., Yi, J. & Hsieh, C.-J. Zoo: Zeroth order optimization based black-box attacks to deep neural networks without training substitute models. In Proceedings of the 10th ACM Workshop on Artificial Intelli- gence and Security, 15-26 (2017).
  27. Jiang, S., Lu, S. & Deng, D.-L. Adversarial machine learning phases of matter. arXiv preprint arXiv:1910.13453 (2019). · arXiv
  28. Guo, C., Rana, M., Cisse, M. & Van Der Maaten, L. Coun- tering adversarial images using input transformations. arXiv preprint arXiv:1711.00117 (2017). · arXiv
  29. Buckman, J., Roy, A., Raffel, C. & Goodfellow, I. Ther- mometer encoding: One hot way to resist adversarial exam- ples. In International Conference on Learning Representa- tions (2018).
  30. Feinman, R., Curtin, R. R., Shintre, S. & Gardner, A. B. Detecting adversarial samples from artifacts. arXiv preprint arXiv:1703.00410 (2017). · arXiv
  31. Salman, H., Li, J., Razenshteyn, I., Zhang, P., Zhang, H., Bubeck, S., & Yang, G. Provably robust deep learning via adversarially trained smoothed classifiers. Advances in Neural Information Processing Systems 32 (2019).
  32. Zhang, H., Yu, Y., Jiao, J., Xing, E., El Ghaoui, L., & Jordan, M. Theoretically principled trade-off between robustness and accuracy. In International Conference on Machine Learning, 7472-7482 (PMLR, 2019).
  33. Lecuyer, M., Atlidakis, V., Geambasu, R., Hsu, D. & Jana, S. Certified robustness to adversarial examples with differential privacy. In 2019 IEEE Symposium on Security and Privacy (SP), 656-672 (IEEE, 2019).
  34. Cohen, J., Rosenfeld, E. & Kolter, Z. Certified adversarial robustness via randomized smoothing. In International Con- ference on Machine Learning, 1310-1320 (PMLR, 2019).
  35. Wong, E., Schmidt, F., Metzen, J. H. & Kolter, J. Z. Scaling provable adversarial defenses. Advances in Neural Informa- tion Processing Systems 31 (2018).
  36. Raghunathan, A., Steinhardt, J. & Liang, P. Certi- fied defenses against adversarial examples. arXiv preprint arXiv:1801.09344 (2018). · arXiv
  37. Tran, H.-D., Bak, S., Xiang, W. & Johnson, T. T. Verification of deep convolutional neural networks using imagestars. In Lahiri, S. K. & Wang, C. (eds.) Computer Aided Verification, 18-42 (Springer International Publishing, Cham, 2020).
  38. Elboher, Y. Y., Gottschlich, J. & Katz, G. An abstraction- based framework for neural network verification. In Inter- national Conference on Computer Aided Verification, 43-65 (Springer, 2020).
  39. Fremont, D. J., Chiu, J., Margineantu, D. D., Osipychev, D. & Seshia, S. A. Formal analysis and redesign of a neural network-based aircraft taxiing system with verifai. CoRR abs/2005.07173 (2020). 2005.07173. · arXiv
  40. Zhou, L. & Ying, M. Differential privacy in quantum compu- tation. In 2017 IEEE 30th Computer Security Foundations Symposium (CSF), 249-262 (IEEE, 2017).
  41. Dwork, C. Differential privacy: A survey of results. In Inter- national Conference on Theory and Applications of Models of Computation, 1-19 (Springer, 2008).
  42. Holevo, A. S. Statistical decision theory for quantum systems. Journal of Multivariate Analysis 3, 337-394 (1973).
  43. Kang, D., Sun, Y., Brown, T., Hendrycks, D. & Steinhardt, J. Transfer of adversarial robustness between perturbation types. arXiv preprint arXiv:1905.01034 (2019). · arXiv
  44. Tsipras, D., Santurkar, S., Engstrom, L., Turner, A. & Madry, A. Robustness may be at odds with accuracy. arXiv preprint arXiv:1805.12152 (2018). · arXiv
  45. Schuld, M. Supervised quantum machine learning models are kernel methods. arXiv preprint arXiv:2101.11020 (2021). · arXiv
  46. Dilip, R., Liu, Y.-J., Smith, A. & Pollmann, F. Data compression for quantum machine learning. arXiv preprint arXiv:2204.11170 (2022). · arXiv
  47. Gicev, S., Hollenberg, L. C. & Usman, M. A scalable and fast artificial neural network syndrome decoder for surface codes. arXiv preprint arXiv:2110.05854 (2021). · arXiv
  48. Hu, W. & Tan, Y. Generating adversarial malware exam- ples for black-box attacks based on gan. arXiv preprint arXiv:1702.05983 (2017). · arXiv
  49. Xiao, C., Li, B., Zhu, J. Y., He, W., Liu, M., & Song, D. Generating adversarial examples with adversarial networks. arXiv preprint arXiv:1801.02610 (2018). · arXiv
  50. Samangouei, P., Kabkab, M. & Chellappa, R. Defense-gan: Protecting classifiers against adversarial attacks using gener- ative models. arXiv preprint arXiv:1805.06605 (2018). · arXiv
  51. Shen, S., Jin, G., Gao, K. & Zhang, Y. Ape-gan: Ad- versarial perturbation elimination with gan. arXiv preprint arXiv:1707.05474 (2017). · arXiv
  52. T. Campbell, E. & Howard, M. A unified framework for magic state distillation and multiqubit gate-synthesis with reduced resource cost. arXiv:1606.01904 (2021). · arXiv

Cited by

Sorted by citations

Authors
West, M. T., Tsang, S.-L., Low, J. S., Hill, C. D., Leckie, C., Hollenberg, L. C. L., Erfani, S. M., & Usman, M.
Affiliations
  • The University of Melbourne (AU)
  • Commonwealth Scientific and Industrial Research Organisation (AU)
Corresponding author
  • West, Maxwell T.
  • Usman, Muhammad
ORCID
Venue
Nature Machine Intelligence
Publisher
Springer Science and Business Media LLC
Published
2023-05-25
Volume
5
Issue
6
Pages
581-589
ISSN
2522-5839 (ISSN-L)
DOI
10.1038/s42256-023-00661-1
OpenAlex
W4378212147
Cited by
79
References
14
Citations by year
2026: 23 · 2025: 28 · 2024: 22 · 2023: 6
FWCI
7.45
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Machine Intelligence (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • Minerva Access (University of Melbourne) (submittedVersion)
  • arXiv (Cornell University) (cc-by)
Funders
  • Australian Government
  • Australian Research Council (DE220100680)
  • National Cancer Institute
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Quantum Computing Algorithms and Architecture
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
  • Physical Sciences › Computer Science › Artificial Intelligence › Quantum Information and Cryptography
Keywords
adversarial robustness, adversarial examples, quantum machine learning, quantum advantage, image classification, feature detection

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