A Quantum State Backdoor Attack Against Quantum Neural Networks
Advanced Quantum Technologies · 2026-03 · 9 (3)
DOI: 10.1002/qute.202500791 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Quantum Technologies, online erschienen am 20.03.2026. Verfasst von Jiayu Zhao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Innovative Research Group Project of the National Natural Science Foundation of China.
Abstract (Originalsprache)
Quantum neural networks (QNNs) are advancing rapidly, but their security issues must not be overlooked. Backdoor attacks, as a stealthy and highly threatening attack method, have caused significant impacts on classical neural networks. Moreover, backdoor attacks have recently been proven to pose a significant threat to quantum neural networks as well. Currently, all existing methods in quantum machine learning backdoor research are designed for classical data samples. These methods all involve poisoning classical data samples first and then quantizing them, with no existing approaches that directly target quantum state data for poisoning. This paper presents a novel backdoor attack method against quantum neural networks by utilizing the quantum state—universal adversarial perturbations (QS‐UAP). This method, for the first time, constructs a backdoor trigger specifically for quantum‐state data based on quantum generative models. Moreover, this method enhances the quality of the backdoor trigger by integrating knowledge distillation with frequency‐domain constraints. The proposed method embeds a backdoor into the target model by poisoning quantum data samples. Experimental results demonstrate that with a 10% poisoning rate, the attack success rates exceed 97% across three structurally distinct QNN architectures.
Förderung
- National Natural Science Foundation of China
- Innovative Research Group Project of the National Natural Science Foundation of China
Zitieren
APA
Zhao, J., Yan, L., Tan, D., Chang, Y., & Zhang, S. (2026). A Quantum State Backdoor Attack Against Quantum Neural Networks. Advanced Quantum Technologies, 9(3). https://doi.org/10.1002/qute.202500791
Vancouver
Zhao J, Yan L, Tan D, Chang Y, Zhang S. A Quantum State Backdoor Attack Against Quantum Neural Networks. Advanced Quantum Technologies. 2026;9(3). doi:10.1002/qute.202500791
BibTeX
@article{Zhao2026,
author = {Zhao, Jiayu and Yan, Lili and Tan, Dong and Chang, Yan and Zhang, Shibin},
title = {A Quantum State Backdoor Attack Against Quantum Neural Networks},
journal = {Advanced Quantum Technologies},
year = {2026},
volume = {9},
number = {3},
doi = {10.1002/qute.202500791}
}
EUVIMED