EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing quantum adversarial robustness by randomized encodings

Weiyuan Gong, Dong Yuan, Weikang Li, Dong-Ling Deng

Physical Review Research · 04.04.2024 · 6 (2)

DOI: 10.1103/physrevresearch.6.023020 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physical Review Research, online erschienen am 04.04.2024. Verfasst von Weiyuan Gong und 3 weiteren Autor:innen. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 99 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Tsinghua University, Innovation Program for Quantum Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The interplay between quantum physics and machine learning gives rise to the emergent frontier of quantum machine learning, where advanced quantum learning models may outperform their classical counterparts in solving certain challenging problems. However, quantum learning systems are vulnerable to adversarial attacks: adding tiny carefully crafted perturbations on legitimate input samples can cause misclassifications. To address this problem, we propose an effective approach to protect quantum learning systems from adversarial attacks by randomly encoding the legitimate data samples through unitary or quantum error correction encoders that are unknown to the attackers. In particular, we rigorously prove that both global and local random unitary encoders lead to exponentially vanishing gradients (i.e., barren plateaus) for any variational quantum circuits that aim to add adversarial perturbations, independent of the input data and the inner structures of adversarial circuits and quantum classifiers. In addition, we prove a rigorous bound on the vulnerability of quantum classifiers under local unitary adversarial attacks. We show that random black-box quantum error correction encoders can protect quantum classifiers against local adversarial noises and their robustness increases as we concatenate error correction codes. To quantify the robustness enhancement, we adapt quantum differential privacy as a measure of the prediction stability for quantum classifiers. Our results establish versatile defense strategies for quantum classifiers against adversarial perturbations, which provide valuable guidance to enhance the reliability and security for both near-term and future quantum learning technologies. Published by the American Physical Society 2024

Förderung

  • National Natural Science Foundation of China
  • Tsinghua University
  • Innovation Program for Quantum Science and Technology

Zitieren

APA

Gong, W., Yuan, D., Li, W., & Deng, D. (2024). Enhancing quantum adversarial robustness by randomized encodings. Physical Review Research, 6(2). https://doi.org/10.1103/physrevresearch.6.023020

Vancouver

Gong W, Yuan D, Li W, Deng D. Enhancing quantum adversarial robustness by randomized encodings. Physical Review Research. 2024;6(2). doi:10.1103/physrevresearch.6.023020

BibTeX
@article{Gong2024,
  author = {Gong, Weiyuan and Yuan, Dong and Li, Weikang and Deng, Dong-Ling},
  title = {Enhancing quantum adversarial robustness by randomized encodings},
  journal = {Physical Review Research},
  year = {2024},
  volume = {6},
  number = {2},
  doi = {10.1103/physrevresearch.6.023020}
}
Kostenlos starten →