Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Predominant Aspects on Security for Quantum Machine Learning: Literature Review (2401.07774v3)

Published 15 Jan 2024 in quant-ph and cs.CR

Abstract: Quantum Machine Learning (QML) has emerged as a promising intersection of quantum computing and classical machine learning, anticipated to drive breakthroughs in computational tasks. This paper discusses the question which security concerns and strengths are connected to QML by means of a systematic literature review. We categorize and review the security of QML models, their vulnerabilities inherent to quantum architectures, and the mitigation strategies proposed. The survey reveals that while QML possesses unique strengths, it also introduces novel attack vectors not seen in classical systems. We point out specific risks, such as cross-talk in superconducting systems and forced repeated shuttle operations in ion-trap systems, which threaten QML's reliability. However, approaches like adversarial training, quantum noise exploitation, and quantum differential privacy have shown potential in enhancing QML robustness. Our review discuss the need for continued and rigorous research to ensure the secure deployment of QML in real-world applications. This work serves as a foundational reference for researchers and practitioners aiming to navigate the security aspects of QML.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (69)
  1. Peter W Shor “Algorithms for quantum computation: discrete logarithms and factoring” In Proceedings 35th annual symposium on foundations of computer science, 1994, pp. 124–134 Ieee
  2. Lov K Grover “A fast quantum mechanical algorithm for database search” In Proceedings of the twenty-eighth annual ACM symposium on Theory of computing, 1996, pp. 212–219
  3. John Preskill “Quantum computing in the NISQ era and beyond” In Quantum 2 Verein zur Förderung des Open Access Publizierens in den Quantenwissenschaften, 2018, pp. 79
  4. Seth Lloyd, Masoud Mohseni and Patrick Rebentrost “Quantum principal component analysis” In Nature Physics 10.9 Nature Publishing Group UK London, 2014, pp. 631–633
  5. Maria Schuld, Ilya Sinayskiy and Francesco Petruccione “An introduction to quantum machine learning” In Contemporary Physics 56.2 Taylor & Francis, 2015, pp. 172–185
  6. “Quantum machine learning” In Nature 549.7671 Nature Publishing Group UK London, 2017, pp. 195–202
  7. Nathan Wiebe, Ashish Kapoor and Krysta M Svore “Quantum deep learning” In arXiv preprint arXiv:1412.3489, 2014
  8. “Quantum reinforcement learning” In IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 38.5 IEEE, 2008, pp. 1207–1220
  9. “Security Aspects of Quantum Machine Learning: Opportunities, Threats and Defenses” In Proceedings of the Great Lakes Symposium on VLSI 2022, GLSVLSI ’22 Irvine, CA, USA: Association for Computing Machinery, 2022, pp. 463–468 DOI: 10.1145/3526241.3530833
  10. Michael A Nielsen and Isaac L Chuang “Quantum computation and quantum information” Cambridge University Press
  11. “Subexponential Factoring Algorithms” In Prime Numbers: A Computational Perspective New York, NY: Springer New York, 2001, pp. 227–283 DOI: 10.1007/978-1-4684-9316-0_6
  12. “Quantum supremacy using a programmable superconducting processor” In Nature 574.7779 Springer ScienceBusiness Media LLC, 2019, pp. 505–510 DOI: 10.1038/s41586-019-1666-5
  13. IBM Quantum “The IBM Quantum Development Roadmap”, 2022 URL: https://www.ibm.com/quantum/roadmap
  14. “Quantum generative adversarial networks” In Physical Review A 98.1 American Physical Society (APS), 2018 DOI: 10.1103/physreva.98.012324
  15. Sirui Lu, Lu-Ming Duan and Dong-Ling Deng “Quantum adversarial machine learning” In Physical Review Research 2.3 APS, 2020, pp. 033212
  16. “Tensor networks and efficient descriptions of classical data”, 2021 arXiv:2103.06872 [quant-ph]
  17. “Parameterized quantum circuits as machine learning models” In Quantum Science and Technology 4.4 IOP Publishing, 2019, pp. 043001 DOI: 10.1088/2058-9565/ab4eb5
  18. “Quantum Machine Learning in Feature Hilbert Spaces” In Physical Review Letters 122.4 American Physical Society (APS), 2019 DOI: 10.1103/physrevlett.122.040504
  19. “Supervised learning with quantum computers” Springer
  20. “Vulnerability of quantum classification to adversarial perturbations” In Physical Review A 101.6 APS, 2020, pp. 062331
  21. “Certified Robustness of Quantum Classifiers against Adversarial Examples through Quantum Noise”, 2023 arXiv:2211.00887 [quant-ph]
  22. “Robust in practice: Adversarial attacks on quantum machine learning” In Physical Review A 103.4 APS, 2021, pp. 042427
  23. “Experimental quantum adversarial learning with programmable superconducting qubits” In Nature Computational Science 2.11 Springer ScienceBusiness Media LLC, 2022, pp. 711–717 DOI: 10.1038/s43588-022-00351-9
  24. “The power of quantum neural networks” In Nature Computational Science 1.6 Springer ScienceBusiness Media LLC, 2021, pp. 403–409 DOI: 10.1038/s43588-021-00084-1
  25. Korn Sooksatra, Pablo Rivas and Javier Orduz “Evaluating accuracy and adversarial robustness of quanvolutional neural networks” In 2021 International Conference on Computational Science and Computational Intelligence (CSCI), 2021, pp. 152–157 IEEE
  26. “Robustness of quantum reinforcement learning under hardware errors” In EPJ Quantum Technology 10.1 SpringerOpen, 2023, pp. 1–43
  27. “Generation of High-Resolution Handwritten Digits with an Ion-Trap Quantum Computer”, 2022 arXiv:2012.03924 [quant-ph]
  28. Christa Zoufal, Aurélien Lucchi and Stefan Woerner “Variational quantum Boltzmann machines” In Quantum Machine Intelligence 3.1 Springer ScienceBusiness Media LLC, 2021 DOI: 10.1007/s42484-020-00033-7
  29. “Defence against adversarial attacks using classical and quantum-enhanced Boltzmann machines” In Machine Learning: Science and Technology 2.4 IOP Publishing, 2021, pp. 045006
  30. “Power of data in quantum machine learning” In Nature Communications 12.1 Springer ScienceBusiness Media LLC, 2021 DOI: 10.1038/s41467-021-22539-9
  31. “Extension of the PRISMA 2020 statement for living systematic reviews (LSRs): protocol [version 2; peer review: 1 approved]” In F1000Research 11.109, 2022 DOI: 10.12688/f1000research.75449.2
  32. “QTROJAN: A Circuit Backdoor Against Quantum Neural Networks” In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023, pp. 1–5 IEEE
  33. “QDoor: Exploiting Approximate Synthesis for Backdoor Attacks in Quantum Neural Networks” In 2023 IEEE International Conference on Quantum Computing and Engineering (QCE) 1, 2023, pp. 1098–1106 IEEE
  34. Abdullah Ash Saki, Mahabubul Alam and Swaroop Ghosh “Impact of noise on the resilience and the security of quantum computing” In 2021 22nd International Symposium on Quality Electronic Design (ISQED), 2021, pp. 186–191 IEEE
  35. Abdullah Ash Saki, Rasit Onur Topaloglu and Swaroop Ghosh “Shuttle-Exploiting Attacks and Their Defenses in Trapped-Ion Quantum Computers”, 2021 arXiv:2108.01054 [quant-ph]
  36. “Special Session: On the Reliability of Conventional and Quantum Neural Network Hardware” In 2022 IEEE 40th VLSI Test Symposium (VTS), 2022, pp. 1–12 DOI: 10.1109/VTS52500.2021.9794194
  37. Mahabubul Alam, Abdullah Ash-Saki and Swaroop Ghosh “Addressing Temporal Variations in Qubit Quality Metrics for Parameterized Quantum Circuits” In 2019 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED), 2019, pp. 1–6 DOI: 10.1109/ISLPED.2019.8824907
  38. “Universal adversarial examples and perturbations for quantum classifiers” In National Science Review 9.6 Oxford University Press, 2022, pp. nwab130
  39. “Towards an Antivirus for Quantum Computers” In 2022 IEEE International Symposium on Hardware Oriented Security and Trust (HOST) 13, 2023, pp. 37–40 DOI: 10.1109/HOST54066.2022.9840181
  40. Ellis Wilson, Sudhakar Singh and Frank Mueller “Just-in-time Quantum Circuit Transpilation Reduces Noise”, 2020 arXiv:2005.12820 [quant-ph]
  41. Kyle Poland, Kerstin Beer and Tobias J Osborne “No free lunch for quantum machine learning” In arXiv preprint arXiv:2003.14103, 2020
  42. Leonardo Banchi “Robust quantum classifiers via NISQ adversarial learning” In Nature Computational Science 2.11 Nature Publishing Group US New York, 2022, pp. 699–700
  43. “Exploring the Vulnerabilities of Machine Learning and Quantum Machine Learning to Adversarial Attacks using a Malware Dataset: A Comparative Analysis” In IEEE CARL K. CHANG SYMPOSIUM ON SOFTWARE SERVICES ENGINEERING, 2023
  44. “Benchmarking adversarially robust quantum machine learning at scale” In Physical Review Research 5.2 American Physical Society (APS), 2023 DOI: 10.1103/physrevresearch.5.023186
  45. “Improved Differential Privacy Noise Mechanism in Quantum Machine Learning” In IEEE Access IEEE, 2023
  46. “Enhancing Quantum Adversarial Robustness by Randomized Encodings”, 2022 arXiv:2212.02531 [quant-ph]
  47. “Quantum noise protects quantum classifiers against adversaries” In Physical Review Research 3.2 APS, 2021, pp. 023153
  48. “Optimal provable robustness of quantum classification via quantum hypothesis testing” In npj Quantum Information 7.1 Springer ScienceBusiness Media LLC, 2021 DOI: 10.1038/s41534-021-00410-5
  49. Christoph Hirche, Cambyse Rouzé and Daniel Stilck França “Quantum differential privacy: An information theory perspective” In IEEE Transactions on Information Theory IEEE, 2023
  50. “Adversarial Robustness based on Randomized Smoothing in Quantum Machine Learning”, 2023 URL: https://openreview.net/forum?id=o-Yxq5iicIp
  51. “Expressive variational quantum circuits provide inherent privacy in federated learning”, 2023 arXiv:2309.13002 [quant-ph]
  52. “Quantum Robustness Verification: A Hybrid Quantum-Classical Neural Network Certification Algorithm” In 2022 IEEE International Conference on Quantum Computing and Engineering (QCE), 2022, pp. 142–153 IEEE
  53. “Efficient milp decomposition in quantum computing for relu network robustness” In 2023 IEEE International Conference on Quantum Computing and Engineering (QCE) 1, 2023, pp. 524–534 IEEE
  54. Khashayar Barooti, Grzegorz Głuch and Ruediger Urbanke “Provable Adversarial Robustness in the Quantum Model”, 2021 arXiv:2112.09625 [quant-ph]
  55. Ji Guan, Wang Fang and Mingsheng Ying “Robustness Verification of Quantum Machine Learning.” In CoRR, 2020
  56. Ji Guan, Wang Fang and Mingsheng Ying “Robustness verification of quantum classifiers” In Computer Aided Verification: 33rd International Conference, CAV 2021, Virtual Event, July 20–23, 2021, Proceedings, Part I 33, 2021, pp. 151–174 Springer
  57. Ji Guan, Wang Fang and Mingsheng Ying “Verifying Fairness in Quantum Machine Learning” In International Conference on Computer Aided Verification, 2022, pp. 408–429 Springer
  58. Ian Goodfellow, Jonathon Shlens and Christian Szegedy “Explaining and Harnessing Adversarial Examples” In International Conference on Learning Representations, 2015 URL: http://arxiv.org/abs/1412.6572
  59. Alexey Kurakin, Ian J Goodfellow and Samy Bengio “Adversarial examples in the physical world” In Artificial intelligence safety and security ChapmanHall/CRC, 2018, pp. 99–112
  60. “Towards Deep Learning Models Resistant to Adversarial Attacks” In International Conference on Learning Representations, 2018 URL: https://openreview.net/forum?id=rJzIBfZAb
  61. “Boosting adversarial attacks with momentum” In Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 9185–9193
  62. “Quantum adversarial metric learning model based on triplet loss function”, 2023 arXiv:2303.08293 [quant-ph]
  63. “MNIST handwritten digit database”, http://yann.lecun.com/exdb/mnist/, 2010 URL: http://yann.lecun.com/exdb/mnist/
  64. “Adversarial robustness in hybrid quantum-classical deep learning for botnet dga detection” In Journal of Information Processing 30 Information Processing Society of Japan, 2022, pp. 636–644
  65. Cynthia Dwork “Differential privacy” In International colloquium on automata, languages, and programming, 2006, pp. 1–12 Springer
  66. “Deep learning with differential privacy” In Proceedings of the 2016 ACM SIGSAC conference on computer and communications security, 2016, pp. 308–318
  67. Jeremy Cohen, Elan Rosenfeld and Zico Kolter “Certified adversarial robustness via randomized smoothing” In international conference on machine learning, 2019, pp. 1310–1320 PMLR
  68. “Differential privacy in quantum computation” In 2017 IEEE 30th Computer Security Foundations Symposium (CSF) IEEE, 2017, pp. 249–262
  69. Maria Schuld, Ryan Sweke and Johannes Jakob Meyer “Effect of data encoding on the expressive power of variational quantum-machine-learning models” In Physical Review A 103.3 American Physical Society (APS), 2021 DOI: 10.1103/physreva.103.032430
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (7)
  1. Nicola Franco (12 papers)
  2. Alona Sakhnenko (6 papers)
  3. Leon Stolpmann (1 paper)
  4. Daniel Thuerck (2 papers)
  5. Fabian Petsch (1 paper)
  6. Annika Rüll (1 paper)
  7. Jeanette Miriam Lorenz (37 papers)
Citations (6)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets