Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash 82 tok/s
Gemini 2.5 Pro 49 tok/s Pro
GPT-5 Medium 18 tok/s
GPT-5 High 12 tok/s Pro
GPT-4o 96 tok/s
GPT OSS 120B 467 tok/s Pro
Kimi K2 217 tok/s Pro
2000 character limit reached

Quantum Adversarial Learning for Kernel Methods (2404.05824v1)

Published 8 Apr 2024 in quant-ph, cs.CR, and cs.LG

Abstract: We show that hybrid quantum classifiers based on quantum kernel methods and support vector machines are vulnerable against adversarial attacks, namely small engineered perturbations of the input data can deceive the classifier into predicting the wrong result. Nonetheless, we also show that simple defence strategies based on data augmentation with a few crafted perturbations can make the classifier robust against new attacks. Our results find applications in security-critical learning problems and in mitigating the effect of some forms of quantum noise, since the attacker can also be understood as part of the surrounding environment.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (15)
  1. B. Biggio and F. Roli, Wild patterns: Ten years after the rise of adversarial machine learning, in Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security (2018) pp. 2154–2156.
  2. M. Schuld, I. Sinayskiy, and F. Petruccione, An introduction to quantum machine learning, Contemporary Physics 56, 172 (2015).
  3. S. Lu, L.-M. Duan, and D.-L. Deng, Quantum adversarial machine learning, Physical Review Research 2, 033212 (2020).
  4. N. Liu and P. Wittek, Vulnerability of quantum classification to adversarial perturbations, Physical Review A 101, 062331 (2020).
  5. Qiskit contributors, Qiskit: An open-source framework for quantum computing (2023).
  6. M. Schuld and F. Petruccione, Machine learning with quantum computers (Springer, 2021).
  7. N. Cristianini and J. Shawe-Taylor, An introduction to support vector machines and other kernel-based learning methods (Cambridge university press, 2000).
  8. Y. Liu, S. Arunachalam, and K. Temme, A rigorous and robust quantum speed-up in supervised machine learning, Nature Physics 17, 1013 (2021).
  9. C.-C. Chang and C.-J. Lin, Libsvm: a library for support vector machines, ACM transactions on intelligent systems and technology (TIST) 2, 1 (2011).
  10. S. Thanasilp, S. Wang, and Z. Holmes, Exponential concentration and untrainability in quantum kernel methods, arXiv preprint arXiv:2208.11060  (2022).
  11. L. Banchi and G. E. Crooks, Measuring analytic gradients of general quantum evolution with the stochastic parameter shift rule, Quantum 5, 386 (2021).
  12. L. Banchi, Robust quantum classifiers via nisq adversarial learning, Nature Computational Science 2, 699 (2022).
  13. L. Banchi, J. Pereira, and S. Pirandola, Generalization in quantum machine learning: A quantum information standpoint, PRX Quantum 2, 040321 (2021).
  14. P. Georgiou, S. T. Jose, and O. Simeone, Adversarial quantum machine learning: An information-theoretic generalization analysis, arXiv preprint arXiv:2402.00176  (2024).
  15. T. Wang, D. Zhao, and S. Tian, An overview of kernel alignment and its applications, Artificial Intelligence Review 43, 179 (2015).
Citations (2)
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

Summary

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

Ai Generate Text Spark Streamline Icon: https://streamlinehq.com

Paper Prompts

Sign up for free to create and run prompts on this paper using GPT-5.

Dice Question Streamline Icon: https://streamlinehq.com

Follow-up Questions

We haven't generated follow-up questions for this paper yet.

X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets