CopyQNN: Quantum Neural Network Extraction Attack under Varying Quantum Noise

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fu, Zhenxiao, Zhao, Leyi, Zhang, Xuhong, Xu, Yilun, Huang, Gang, Chen, Fan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910900375519232
author Fu, Zhenxiao
Zhao, Leyi
Zhang, Xuhong
Xu, Yilun
Huang, Gang
Chen, Fan
author_facet Fu, Zhenxiao
Zhao, Leyi
Zhang, Xuhong
Xu, Yilun
Huang, Gang
Chen, Fan
contents Quantum Neural Networks (QNNs) have shown significant value across domains, with well-trained QNNs representing critical intellectual property often deployed via cloud-based QNN-as-a-Service (QNNaaS) platforms. Recent work has examined QNN model extraction attacks using classical and emerging quantum strategies. These attacks involve adversaries querying QNNaaS platforms to obtain labeled data for training local substitute QNNs that replicate the functionality of cloud-based models. However, existing approaches have largely overlooked the impact of varying quantum noise inherent in noisy intermediate-scale quantum (NISQ) computers, limiting their effectiveness in real-world settings. To address this limitation, we propose the CopyQNN framework, which employs a three-step data cleaning method to eliminate noisy data based on its noise sensitivity. This is followed by the integration of contrastive and transfer learning within the quantum domain, enabling efficient training of substitute QNNs using a limited but cleaned set of queried data. Experimental results on NISQ computers demonstrate that a practical implementation of CopyQNN significantly outperforms state-of-the-art QNN extraction attacks, achieving an average performance improvement of 8.73% across all tasks while reducing the number of required queries by 90x, with only a modest increase in hardware overhead.
format Preprint
id arxiv_https___arxiv_org_abs_2504_00366
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CopyQNN: Quantum Neural Network Extraction Attack under Varying Quantum Noise
Fu, Zhenxiao
Zhao, Leyi
Zhang, Xuhong
Xu, Yilun
Huang, Gang
Chen, Fan
Quantum Physics
Cryptography and Security
Machine Learning
Quantum Neural Networks (QNNs) have shown significant value across domains, with well-trained QNNs representing critical intellectual property often deployed via cloud-based QNN-as-a-Service (QNNaaS) platforms. Recent work has examined QNN model extraction attacks using classical and emerging quantum strategies. These attacks involve adversaries querying QNNaaS platforms to obtain labeled data for training local substitute QNNs that replicate the functionality of cloud-based models. However, existing approaches have largely overlooked the impact of varying quantum noise inherent in noisy intermediate-scale quantum (NISQ) computers, limiting their effectiveness in real-world settings. To address this limitation, we propose the CopyQNN framework, which employs a three-step data cleaning method to eliminate noisy data based on its noise sensitivity. This is followed by the integration of contrastive and transfer learning within the quantum domain, enabling efficient training of substitute QNNs using a limited but cleaned set of queried data. Experimental results on NISQ computers demonstrate that a practical implementation of CopyQNN significantly outperforms state-of-the-art QNN extraction attacks, achieving an average performance improvement of 8.73% across all tasks while reducing the number of required queries by 90x, with only a modest increase in hardware overhead.
title CopyQNN: Quantum Neural Network Extraction Attack under Varying Quantum Noise
topic Quantum Physics
Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2504.00366