pith. sign in

arxiv: 2605.18821 · v1 · pith:CLMOKQBAnew · submitted 2026-05-12 · 💻 cs.LG · cs.CR

Quantum Adversarial Machine Learning: From Classical Adaptations to Quantum-Native Methods

Roozbeh Razavi-Far , Mohammad Meymani , Erfan Mahmoudinia , Dorsa Vazirzade , Peyman Paknezhad , Fateme Ghasemi , Saeed Saravani , Somayeh Nikkhoo
show 1 more author
Kimia Haghjooei
This is my paper

Pith reviewed 2026-05-20 22:23 UTC · model grok-4.3

classification 💻 cs.LG cs.CR
keywords quantum adversarial machine learningadversarial attacksquantum machine learningcountermeasuresdefense strategiesvulnerabilitiessurvey
0
0 comments X

The pith

Quantum adversarial machine learning studies vulnerabilities in quantum ML models along with attacks and quantum-enhanced defenses.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper surveys the emerging intersection of quantum machine learning and adversarial threats. It reviews how quantum models can be attacked and the countermeasures that use quantum techniques to protect them. The authors cover theoretical foundations, current attack methods, defense strategies, trends, and open challenges. A sympathetic reader would care because quantum ML promises performance gains on hard tasks yet inherits and possibly amplifies security weaknesses that must be understood before large-scale deployment.

Core claim

Given recent advancements in quantum computing and machine learning, the quantum adversarial machine learning field has emerged to study the vulnerabilities of quantum machine learning, possible attacks, and novel quantum-enhanced defense strategies; the survey supplies a detailed overview of these attacks, countermeasures, theoretical underpinnings, emerging trends, and critical challenges.

What carries the argument

A structured literature review that organizes attacks on quantum machine learning models and the corresponding quantum-enhanced countermeasures.

If this is right

  • Researchers gain a map of known attack vectors that can guide development of more robust quantum classifiers and generative models.
  • Quantum-native defense strategies become candidates for implementation once hardware supports deeper circuits.
  • Identified critical challenges point to concrete directions for future theoretical and experimental work in the area.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • As quantum devices grow in size and fidelity, adversarial robustness may become a standard evaluation metric alongside accuracy.
  • Hybrid classical-quantum defense pipelines could emerge by combining the surveyed quantum methods with established classical techniques.
  • Standardized benchmark datasets and attack suites for quantum ML would help compare the effectiveness of the reviewed countermeasures.

Load-bearing premise

The current body of literature on quantum adversarial machine learning is mature enough to support a detailed and representative overview of attacks, countermeasures, and challenges.

What would settle it

A major new attack type, defense method, or body of unpublished work that the survey omits or that shows the field remains too immature for a comprehensive review.

read the original abstract

Machine learning has revolutionized numerous industrial domains. Despite recent advances, machine learning models remain vulnerable to adversarial threats. Adversarial machine learning is a field that studies these vulnerabilities to build robust machine learning models. Quantum machine learning is an interdisciplinary field that bridges quantum computing and classical machine learning. While quantum machine learning shows potentials to outperform classical machine learning in complex tasks such as regression, classification, and generative modeling, it remains vulnerable to adversarial attacks. Given the recent advancements in quantum computing and machine learning, the quantum adversarial machine learning field has emerged to study the vulnerabilities of quantum machine learning, possible attacks, and novel quantum-enhanced defense strategies. In this survey, we provide a detailed overview on quantum adversarial machine learning and explore the existing attacks and countermeasures. We also review the theoretical underpinnings of this area, emerging trends, and critical challenges.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 1 minor

Summary. This manuscript is a survey on the emerging field of quantum adversarial machine learning. It reviews vulnerabilities of quantum machine learning models, catalogs attacks adapted from classical adversarial ML as well as quantum-native threats, examines defense strategies including quantum-enhanced countermeasures, and discusses theoretical underpinnings, trends, and open challenges.

Significance. If the coverage is representative, the survey would be a useful consolidation for an interdisciplinary area that is still forming. It could help researchers map the landscape of attacks on variational quantum circuits and quantum kernels, identify gaps between classical adaptations and truly quantum-native methods, and highlight directions for robust quantum ML. The value hinges on whether the reviewed literature forms a balanced sample of the limited but growing body of work.

major comments (1)
  1. [Abstract and §1] Abstract and §1: The central claim that the paper supplies a 'detailed overview' of attacks, countermeasures, theoretical underpinnings, trends, and challenges rests on an unstated literature-review protocol. No search strategy, databases, keywords, inclusion/exclusion criteria, or cutoff date are provided. In an explicitly 'emerging' field with sparse prior literature, this omission makes it impossible to assess whether important works on quantum-specific gradient attacks, circuit poisoning, or variational defenses have been omitted or over-weighted, directly affecting the reliability of the synthesis.
minor comments (1)
  1. The distinction between 'classical adaptations' and 'quantum-native methods' is introduced but not consistently applied when classifying individual attacks and defenses; a clear taxonomy table would improve readability.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback and positive evaluation of the manuscript's potential utility in consolidating this emerging interdisciplinary area. We address the major comment below and will revise the manuscript to improve transparency.

read point-by-point responses

  1. Referee: [Abstract and §1] Abstract and §1: The central claim that the paper supplies a 'detailed overview' of attacks, countermeasures, theoretical underpinnings, trends, and challenges rests on an unstated literature-review protocol. No search strategy, databases, keywords, inclusion/exclusion criteria, or cutoff date are provided. In an explicitly 'emerging' field with sparse prior literature, this omission makes it impossible to assess whether important works on quantum-specific gradient attacks, circuit poisoning, or variational defenses have been omitted or over-weighted, directly affecting the reliability of the synthesis.

    Authors: We agree that explicitly documenting the literature review protocol would strengthen the survey, especially given the field's emerging nature and limited body of work. In the revised version, we will add a dedicated paragraph (or short subsection) early in Section 1 that describes our review methodology. This will specify: the databases and repositories searched (arXiv, Google Scholar, IEEE Xplore, and proceedings from quantum computing venues such as QIP and AQIS); the primary keywords and Boolean combinations used (e.g., 'quantum adversarial machine learning', 'adversarial attacks on variational quantum circuits', 'quantum kernel robustness', 'quantum-native attacks'); the inclusion criteria (peer-reviewed articles and preprints that directly examine vulnerabilities, attacks, or defenses in quantum machine learning models, including both classical adaptations and quantum-specific methods); the exclusion criteria (purely classical adversarial ML papers without quantum components, or works focused solely on quantum advantage without adversarial considerations); and the literature cutoff date. We will also briefly note how we handled the sparse literature to avoid over- or under-representation. This addition will enable readers to evaluate coverage of topics such as quantum-specific gradient attacks, circuit poisoning, and variational defenses. We will cross-check the current references against these criteria and incorporate any qualifying works that were inadvertently omitted. revision: yes

Circularity Check

0 steps flagged

Survey aggregates prior literature with no internal derivations or self-referential steps

full rationale

This paper is a literature survey on quantum adversarial machine learning. It reviews existing attacks, countermeasures, theoretical underpinnings, trends, and challenges by citing prior works rather than deriving new results from its own equations or assumptions. No predictions, fitted parameters, uniqueness theorems, or ansatzes are introduced that could reduce to the paper's inputs by construction. The overview claim rests on synthesis of external references, making the structure self-contained against external benchmarks with no circularity.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

As a survey, the paper introduces no new free parameters, axioms, or invented entities and instead relies on the body of prior literature in quantum computing and adversarial ML.

pith-pipeline@v0.9.0 · 5715 in / 885 out tokens · 48762 ms · 2026-05-20T22:23:51.804592+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

150 extracted references · 150 canonical work pages · 7 internal anchors

  1. [1]

    Shinde, S

    P.P. Shinde, S. Shah,A review of machine learning and deep learning applications, in2018 Fourth international conference on computing communication control and automation (ICCUBEA) (IEEE, 2018), pp. 1–6

    work page 2018

  2. [2]

    Pitropakis, E

    N. Pitropakis, E. Panaousis, T. Giannetsos, E. Anastasiadis, G. Loukas, A taxonomy and survey of attacks against machine learning. Computer Science Review34, 100199 (2019) 45

    work page 2019

  3. [3]

    Adversarial Machine Learning at Scale

    A. Kurakin, I. Goodfellow, S. Bengio, Adversarial machine learning at scale. arXiv preprint arXiv:1611.01236 (2016)

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  4. [4]

    D. Kaur, S. Uslu, K.J. Rittichier, A. Durresi, Trustworthy artificial intelligence: a review. ACM computing surveys (CSUR)55(2), 1–38 (2022)

    work page 2022

  5. [5]

    Vashagh, R

    A. Vashagh, R. Razavi-Far, M. Meymani, B. Biggio, Recent advances in adversarial attacks on model utility, privacy, and explainability: A comprehensive survey. Authorea Preprints (2026)

    work page 2026

  6. [6]

    Meymani, R

    M. Meymani, R. Razavi-Far, Divided we fall: Defending against adversarial attacks via soft-gated fractional mixture-of-experts with randomized adversarial training. Information Sciences p. 123427 (2026)

    work page 2026

  7. [7]

    Leading ai progress: Policy insights and a u.s

    Bipartisan House Task Force on Artificial Intelligence. Leading ai progress: Policy insights and a u.s. vision for ai adoption, responsible innovation, and governance (2024). URL https://obernolte.house. gov/AITFReport. Report of the Bipartisan House AI Task Force, 118th Congress

    work page 2024

  8. [8]

    Kusnezov, Y

    D. Kusnezov, Y. Barsoum, E. Begoli, A. Henninger, A. Sadovnik. Risks and mitigation strategies for adversarial artificial intelligence threats: A dhs s&t study preparedness series (2023)

    work page 2023

  9. [9]

    Rietsche, C

    R. Rietsche, C. Dremel, S. Bosch, L. Steinacker, M. Meckel, J.M. Leimeister, Quantum computing. Electronic Markets32(4), 2525–2536 (2022)

    work page 2022

  10. [10]

    Sooksatra, P

    K. Sooksatra, P. Rivas, J. Orduz,Evaluating accuracy and adversarial robustness of quanvolutional neural networks, in2021 International conference on computational science and computational intelligence (CSCI)(IEEE, 2021), pp. 152–157

    work page 2021

  11. [11]

    Ghosh, S

    A. Ghosh, S. Kundu, S. Ghosh, Adversarial threats in quantum machine learning: A survey of attacks and defenses. arXiv preprint arXiv:2506.21842 (2025)

    work page arXiv 2025

  12. [12]

    Franco, A

    N. Franco, A. Sakhnenko, L. Stolpmann, D. Thuerck, F. Petsch, A. R¨ ull, J.M. Lorenz,Predominant aspects on security for quantum machine learning: Literature review, in2024 IEEE International Conference on Quantum Computing and Engineering (QCE), vol. 1 (IEEE, 2024), pp. 1467–1477

    work page 2024

  13. [13]

    West, S.L

    M.T. West, S.L. Tsang, J.S. Low, C.D. Hill, C. Leckie, L.C. Hollenberg, S.M. Erfani, M. Usman, Towards quantum enhanced adversarial robustness in machine learning. Nature Machine Intelligence 5(6), 581–589 (2023)

    work page 2023

  14. [14]

    S. Lu, L.M. Duan, D.L. Deng, Quantum adversarial machine learning. Phys. Rev. Res.2, 033212 (2020). https://doi.org/10.1103/PhysRevResearch.2.033212. URL https://link.aps.org/doi/10.1103/ PhysRevResearch.2.033212

    work page doi:10.1103/physrevresearch.2.033212 2020

  15. [15]

    Zhang, Z.Y

    H.F. Zhang, Z.Y. Chen, P. Wang, L.L. Guo, T.L. Wang, X.Y. Yang, ..., G.P. Guo. Experimental robustness benchmark of quantum neural network on a superconducting quantum processor (2025)

    work page 2025

  16. [16]

    J. Tian, X. Sun, Y. Du, S. Zhao, Q. Liu, K. Zhang, W. Yi, W. Huang, C. Wang, X. Wu, et al., Recent advances for quantum neural networks in generative learning. IEEE Transactions on Pattern Analysis and Machine Intelligence45(10), 12321–12340 (2023)

    work page 2023

  17. [17]

    T. Xiao, X. Zhai, X. Wu, J. Fan, G. Zeng, Practical advantage of quantum machine learning in ghost imaging. Communications Physics6(1), 171 (2023)

    work page 2023

  18. [18]

    Z. Tian, L. Cui, J. Liang, S. Yu, A comprehensive survey on poisoning attacks and countermeasures in machine learning. ACM Computing Surveys55(8), 1–35 (2022)

    work page 2022

  19. [19]

    Arias, I

    D. Arias, I. Garc´ ıa Rodr´ ıguez de Guzm´ an, M. Rodr´ ıguez, E.B. Terres, B. Sanz, J. Gaviria de la Puerta, I. Pastor, A. Zubillaga, P. Garc´ ıa Bringas, Let’s do it right the first time: Survey on security concerns in the way to quantum software engineering (2023). Appears in Communications in Computer and Information Science, vol 1851

    work page 2023

  20. [20]

    Edwards, D.B

    D. Edwards, D.B. Rawat,Quantum Adversarial Machine Learning: Status, Challenges and Perspec- tives, in2020 Second IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA)(2020), pp. 128–133. https://doi.org/10.1109/TPS-ISA50397. 2020.00028 46

    work page doi:10.1109/tps-isa50397 2020

  21. [21]

    C. Xu, F. Erata, J. Szefer. Classification of quantum computer fault injection attacks (2023)

    work page 2023

  22. [22]

    Quantum Adversarial Machine Learning and Defense Strategies: Challenges and Opportunities

    E. Yocam, A. Rizi, M. Kamepalli, V. Vaidyan, Y. Wang, G. Comert, Quantum adversarial machine learning and defense strategies: Challenges and opportunities. arXiv preprint arXiv:2412.12373 (2024)

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  23. [23]

    H. Xu, T. Xiao, J. Huang, M. He, J. Fan, G. Zeng, Toward heisenberg limit without critical slowing down via quantum reinforcement learning. Physical Review Letters134(12), 120803 (2025)

    work page 2025

  24. [24]

    T. Xiao, J. Huang, H. Li, J. Fan, G. Zeng, Quantum generative adversarial imitation learning. New Journal of Physics25(3), 033034 (2023)

    work page 2023

  25. [25]

    Marella, H.S.K

    S.T. Marella, H.S.K. Parisa, Introduction to quantum computing. Quantum Computing and Communications p. 61 (2020)

    work page 2020

  26. [26]

    E. Chae, J. Choi, J. Kim, An elementary review on basic principles and developments of qubits for quantum computing. Nano Convergence11(1), 11 (2024)

    work page 2024

  27. [27]

    M.A. Khan, S. Ghafoor, S.M.H. Zaidi, H. Khan, A. Ahmad, From quantum communication fun- damentals to decoherence mitigation strategies: Addressing global quantum network challenges and projected applications. Heliyon10(14) (2024)

    work page 2024

  28. [28]

    Hughes, J

    C. Hughes, J. Isaacson, A. Perry, R.F. Sun, J. Turner, Quantum computing for the quantum curious (2021)

    work page 2021

  29. [29]

    Mu˜ noz-Coreas, H

    E. Mu˜ noz-Coreas, H. Thapliyal, Everything you always wanted to know about quantum circuits. arXiv preprint arXiv:2208.11725 (2022)

    work page arXiv 2022

  30. [30]

    Palao, R

    J.P. Palao, R. Kosloff, Quantum computing by an optimal control algorithm for unitary transforma- tions. Physical review letters89(18), 188301 (2002)

    work page 2002

  31. [31]

    Schlosshauer, Quantum decoherence

    M. Schlosshauer, Quantum decoherence. Physics Reports831, 1–57 (2019)

    work page 2019

  32. [32]

    Kjaergaard, M.E

    M. Kjaergaard, M.E. Schwartz, J. Braum¨ uller, P. Krantz, J.I.J. Wang, S. Gustavsson, W.D. Oliver, Superconducting qubits: Current state of play. Annual Review of Condensed Matter Physics11(1), 369–395 (2020)

    work page 2020

  33. [33]

    Suzuki, T

    T. Suzuki, T. Hasebe, T. Miyazaki, Quantum support vector machines for classification and regression on a trapped-ion quantum computer. Quantum Machine Intelligence6(1), 31 (2024)

    work page 2024

  34. [34]

    Jeswal, S

    S. Jeswal, S. Chakraverty, Recent developments and applications in quantum neural network: A review. Archives of Computational Methods in Engineering26(4), 793–807 (2019)

    work page 2019

  35. [35]

    Schuld, N

    M. Schuld, N. Killoran, Quantum machine learning in feature hilbert spaces. Physical review letters 122(4), 040504 (2019)

    work page 2019

  36. [36]

    Upadhyay, S

    S. Upadhyay, S. Ghosh,Quantum quandaries: Unraveling encoding vulnerabilities in quantum neu- ral networks, in2025 26th International Symposium on Quality Electronic Design (ISQED)(IEEE, 2025), pp. 1–7

    work page 2025

  37. [37]

    McClean, S

    J.R. McClean, S. Boixo, V.N. Smelyanskiy, R. Babbush, H. Neven, Barren plateaus in quantum neural network training landscapes. Nature communications9(1), 4812 (2018)

    work page 2018

  38. [38]

    Kerenidis, J

    I. Kerenidis, J. Landman, A. Luongo, A. Prakash, q-means: A quantum algorithm for unsupervised machine learning. Advances in neural information processing systems32(2019)

    work page 2019

  39. [39]

    Poggiali, A

    A. Poggiali, A. Berti, A. Bernasconi, G.M. Del Corso, R. Guidotti, Quantum clustering with k-means: A hybrid approach. Theoretical Computer Science992, 114466 (2024)

    work page 2024

  40. [40]

    Skolik, S

    A. Skolik, S. Jerbi, V. Dunjko, Quantum agents in the gym: a variational quantum algorithm for deep q-learning. Quantum6, 720 (2022)

    work page 2022

  41. [41]

    Meyer, C

    N. Meyer, C. Ufrecht, M. Periyasamy, D.D. Scherer, A. Plinge, C. Mutschler, A survey on quantum reinforcement learning. arXiv preprint arXiv:2211.03464 (2022) 47

    work page arXiv 2022

  42. [42]

    S. Li, Y. Fan, X. Li, X. Ruan, Q. Zhao, Z. Peng, R.B. Wu, J. Zhang, P. Song, Robust quantum control using reinforcement learning from demonstration. npj Quantum Information11(1), 124 (2025)

    work page 2025

  43. [43]

    W. Li, D.L. Deng, Recent advances for quantum classifiers. Science China Physics, Mechanics & Astronomy65(2), 220301 (2022)

    work page 2022

  44. [44]

    W. Li, Z.d. Lu, D.L. Deng, Quantum neural network classifiers: A tutorial. SciPost Physics Lecture Notes p. 061 (2022)

    work page 2022

  45. [45]

    Huang, W.J

    S.Y. Huang, W.J. An, D.S. Zhang, N.R. Zhou, Image classification and adversarial robustness anal- ysis based on hybrid quantum–classical convolutional neural network. Optics Communications533, 129287 (2023)

    work page 2023

  46. [46]

    T.G. Tan, J. Zhou, V. Sharma, S.P. Mohanty, Post-quantum adversarial modeling: A user’s perspective. Computer56(8), 58–67 (2023)

    work page 2023

  47. [47]

    Darzi, A.A

    S. Darzi, A.A. Yavuz, Pqc meets ml or ai: Exploring the synergy of machine learning and post- quantum cryptography. Authorea Preprints (2024)

    work page 2024

  48. [48]

    Huynh, J

    L. Huynh, J. Hong, A. Mian, H. Suzuki, Y. Wu, S. Camtepe, Quantum-inspired machine learning: a survey. arXiv preprint arXiv:2308.11269 (2023)

    work page arXiv 2023

  49. [49]

    Kejriwal, A

    D.K. Kejriwal, A. Goel, A. Sharma, Advancing adversarial robustness in cybersecurity: Gradient-free attacks and quantum-inspired defenses for machine learning models. Journal of Innovative Science and Research Technology10(4), 54–65 (2025)

    work page 2025

  50. [50]

    Tseng, W.C

    K.C. Tseng, W.C. Lai, W.C. Huang, Y.C. Chang, S. Zeadally, Ai threats: Adversarial examples with a quantum-inspired algorithm. IEEE Consumer Electronics Magazine (2024)

    work page 2024

  51. [51]

    Marchiori, M

    F. Marchiori, M. Conti,ATTAQ: Adversarial Robustness of Quantum Machine Learning, in 2025 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)(IEEE, 2025), pp. 200–207

    work page 2025

  52. [52]

    N. Liu, P. Wittek, Vulnerability of quantum classification to adversarial perturbations. Physical Review A101(6), 062331 (2020)

    work page 2020

  53. [53]

    B. Li, T. Alpcan, C. Thapa, U. Parampalli, Computable model-independent bounds for adversarial quantum machine learning. IEEE Transactions on Quantum Engineering (2025). Forthcoming

    work page 2025

  54. [54]

    Georgiou, A.M

    P. Georgiou, A.M. Thomas, S.T. Jose, O. Simeone. On the generalization of adversarially trained quantum classifiers (2025)

    work page 2025

  55. [55]

    W. Ren, W. Li, S. Xu, K. Wang, W. Jiang, F. Jin, X. Zhu, J. Chen, Z. Song, P. Zhang, et al. Experimental quantum adversarial learning with programmable superconducting qubits (2022)

    work page 2022

  56. [56]

    Montalbano, L

    G. Montalbano, L. Banchi, Quantum adversarial learning for kernel methods. Quantum Machine Intelligence7(1), 15 (2025)

    work page 2025

  57. [57]

    Kundu, S

    S. Kundu, S. Ghosh,Adversarial Data Poisoning Attack on Quantum Machine Learning in the NISQ Era, inProceedings of the Great Lakes Symposium on VLSI 2025(2025), pp. 976–981

    work page 2025

  58. [58]

    S. Das, S. Ghosh, Randomized reversible gate-based obfuscation for secured compilation of quantum circuit. arXiv preprint arXiv:2305.01133 (2023)

    work page arXiv 2023

  59. [59]

    J. Shi, Z. Xiao, H. Shi, Y. Jiang, X. Li. QuanTest: Entanglement-guided testing of quantum neural network systems (2024)

    work page 2024

  60. [60]

    X. Liu, L. Xie, Y. Wang, J. Zou, J. Xiong, Z. Ying, A. Vasilakos. Privacy and security issues in deep learning: a survey. ieee access 9: 4566–4593 (2021)

    work page 2021

  61. [61]

    Explaining and Harnessing Adversarial Examples

    I.J. Goodfellow, J. Shlens, C. Szegedy, Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014) 48

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  62. [62]

    Towards Deep Learning Models Resistant to Adversarial Attacks

    A. Madry, A. Makelov, L. Schmidt, D. Tsipras, A. Vladu, Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  63. [63]

    El Maouaki, A

    W. El Maouaki, A. Marchisio, T. Said, M. Shafique, M. Bennai. RobQuNNs: A methodology for robust quanvolutional neural networks against adversarial attacks (2024)

    work page 2024

  64. [64]

    West, S.M

    M.T. West, S.M. Erfani, C. Leckie, M. Sevior, L.C. Hollenberg, M. Usman, Benchmarking adver- sarially robust quantum machine learning at scale. Physical Review Research5(2), 023186 (2023)

    work page 2023

  65. [65]

    Papadopoulos, S

    G. Papadopoulos, S. Eloul, Y. Satsangi, J. Heredge, N. Kumar, C.F. Chen, M. Pistoia, A numerical gradient inversion attack in variational quantum neural-networks. arXiv preprint arXiv:2504.12806 (2025)

    work page arXiv 2025

  66. [66]

    A. Jin, T. Dutta, A.T. Ngo, A. Chattopadhyay, M. Mukherjee. Realizing quantum adversarial defense on a trapped-ion quantum processor (2025)

    work page 2025

  67. [67]

    Wiebe, R.S

    N. Wiebe, R.S. Kumar. Hardening quantum machine learning against adversaries (2017)

    work page 2017

  68. [68]

    M.S.H. Onim, H. Thapliyal. Detection of physiological data tampering attacks with quantum machine learning (2025)

    work page 2025

  69. [69]

    S. Das, S. Ghosh, Trojannet: Detecting trojans in quantum circuits using machine learning. arXiv preprint arXiv:2306.16701 (2023)

    work page arXiv 2023

  70. [70]

    Ghosh, S

    A. Ghosh, S. Ghosh,Ai-driven reverse engineering of qml models, in2025 26th International Symposium on Quality Electronic Design (ISQED)(IEEE, 2025), pp. 1–7

    work page 2025

  71. [71]

    Kundu, D

    S. Kundu, D. Kundu, S. Ghosh,Evaluating efficacy of model stealing attacks and defenses on quantum neural networks, inProceedings of the Great Lakes Symposium on VLSI 2024(2024), pp. 556–559

    work page 2024

  72. [72]

    Akter, H

    M.S. Akter, H. Shahriar, I. Iqbal, M. Hossain, M. Karim, V. Clincy, R. Voicu,Exploring the vulnera- bilities of machine learning and quantum machine learning to adversarial attacks using a malware dataset: a comparative analysis, in2023 IEEE International Conference on Software Services Engineering (SSE)(IEEE, 2023), pp. 222–231

    work page 2023

  73. [73]

    Y. Wu, E. Adermann, C. Thapa, S. Camtepe, H. Suzuki, M. Usman. Radio signal classification by adversarially robust quantum machine learning (2023)

    work page 2023

  74. [74]

    Wendlinger, K

    M. Wendlinger, K. Tscharke, P. Debus. A comparative analysis of adversarial robustness for quantum and classical machine learning models (2024)

    work page 2024

  75. [75]

    Baral, B

    B. Baral, B. Bhalgamiya, R. Majumder, D.D. Roy, T.D. Roy, Adversarial attacks on hybrid classical- quantum deep learning models for histopathological cancer detection. APL Machine Learning3(3) (2025)

    work page 2025

  76. [76]

    Tiwo, Quantum machine learning for secure financial forecasting: Mitigating data breaches and adversarial exploits

    O.J. Tiwo, Quantum machine learning for secure financial forecasting: Mitigating data breaches and adversarial exploits. Asian Journal of Research in Computer Science18(4), 154–175 (2025)

    work page 2025

  77. [77]

    El Maouaki, A

    W. El Maouaki, A. Marchisio, T. Said, M. Bennai, M. Shafique. AdvQuNN: A methodology for analyzing the adversarial robustness of quanvolutional neural networks (2024)

    work page 2024

  78. [78]

    E. Wang, H. Chaine, X. Wang, A. Ray, T. Wooldridge,Defending Quantum Neural Networks Against Adversarial Attacks with Homomorphic Data Encryption, in2023 International Conference on Computational Science and Computational Intelligence (CSCI)(IEEE, 2023), pp. 816–822

    work page 2023

  79. [79]

    Kurakin, I.J

    A. Kurakin, I.J. Goodfellow, S. Bengio, Adversarial examples in the physical world pp. 99–112 (2018)

    work page 2018

  80. [80]

    Winderl, N

    D. Winderl, N. Franco, J.M. Lorenz. Quantum neural networks under depolarization noise: Exploring white-box attacks and defenses (2023) 49

    work page 2023

Showing first 80 references.