Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2403.10790 · International Joint Conference on Neural Networks (IJCNN)

QuantumLeak: Stealing Quantum Neural Networks from Cloud-based NISQ Machines

Zhenxiao Fu, Min Yang, Cheng Chu, Yilun Xu, Gang Huang, Fan Chen

Published Jun 30, 2024• 13 citations
arXivHTMLPDF

Abstract

Variational quantum circuits (VQCs) have become a powerful tool for implementing Quantum Neural Networks (QNNs), addressing a wide range of complex problems. Well-trained VQCs serve as valuable intellectual assets hosted on cloud-based Noisy Intermediate Scale Quantum (NISQ) computers, making them susceptible to malicious VQC stealing attacks. However, traditional model extraction techniques designed for classical machine learning models encounter challenges when applied to NISQ computers due to significant noise in current devices. In this paper, we introduce QuantumLeak, an effective and accurate QNN model extraction technique from cloud-based NISQ machines. Compared to existing classical model stealing techniques, QuantumLeak improves local VQC accuracy by 4.99%~7.35% across diverse datasets and VQC architectures.

DOI
10.1109/ijcnn60899.2024.10651540

Related papers

CopyQNN: Quantum Neural Network Extraction Attack under Varying Quantum Noise

Zhenxiao Fu, Leyi Zhao, Xuhong Zhang +3 more

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 over-looked 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 90×, with only a modest increase in hardware overhead.

arXiv:2504.00366•International Joint Conference on Neural Networks (IJCNN)•Jun 30, 2025•6 citations

Late Breaking Results: Extracting QNNs from NISQ Computers via Ensemble Learning

Zhenxiao Fu, Fan Chen

The recent success of Quantum Neural Networks (QNNs) prompts model extraction attacks on cloud platforms, even under black-box constraints. These attacks repeatedly query the victim QNN with malicious inputs. However, existing extraction attacks tailored for classical models yield local substitute QNNs with limited performance due to NISQ computer noise. Drawing from bagging-based ensemble learning, which uses independent weak learners to learn from noisy data, we introduce a novel QNN extraction approach. Our experimental results show this quantum ensemble learning approach improves local QNN accuracy by up to 15.09% compared to previous techniques.

ACM/IEEE Design Automation Conference (DAC)•Jun 23, 2024•0 citations

Evaluating Efficacy of Model Stealing Attacks and Defenses on Quantum Neural Networks

Satwik Kundu, Debarshi Kundu, Swaroop Ghosh

Cloud hosting of quantum machine learning (QML) models exposes them to a range of vulnerabilities, the most significant of which is the model stealing attack. In this study, we assess the efficacy of such attacks in the realm of quantum computing. Our findings revealed that model stealing attacks can produce clone models achieving up to 0.9 × and 0.99 × clone test accuracy when trained using Top-1 and Top-k labels, respectively (k: num_classes). To defend against these attacks, we propose: 1) hardware variation-induced perturbation (HVIP) and 2) hardware and architecture variation-induced perturbation (HAVIP). Despite limited success with our defense techniques, it has led to an important discovery: QML models trained on noisy hardwares are naturally resistant to perturbation or obfuscation-based defenses or attacks.

arXiv:2402.11687•ACM Great Lakes Symposium on VLSI (GLSVLSI)•Jun 10, 2024•11 citations

Implementation of Quantum Deep Reinforcement Learning Using Variational Quantum Circuits

S Lokes, C. Sakthi Jay Mahenthar, S Parvatha Kumaran +2 more

With the evolution of technology, the need to solve complex computational problems like machine learning and deep learning has shot up. However, even the most powerful classical supercomputers find it difficult to execute these tasks. Advancements in quantum computing are leading researchers and tech-giants who strive for better quantum circuits to do machine learning tasks. Current works on Quantum Machine Learning (QML) ensure less memory consumption and reduced model parameters. However, it is strenuous to simulate the classical deep learning approach on existing quantum computing devices due to the inflexibility of Deep quantum circuits. Consequently, designing viable quantum algorithms for QML for noisy intermediate-scale quantum (NISQ) devices is essential. The proposed work aims to explore Variational Quantum Circuits (VQC) for Deep Q network-based Reinforcement Learning by remodeling the target network and experience replay into a representation of VQC. In addition, to the reduction in model parameters, quantum information encoding schemes are used to achieve better results than classical neural networks. VQCs are employed for policyselection and decision-making reinforcement learning by approximating the deep Q-value function with target network and experience replay.

International Conference on Trends in Quantum Computing and Emerging Business Technologies (TQCEBT)•Oct 13, 2022•21 citations

Post-Variational Quantum Neural Networks on a Hybrid HPC-QC System

Maxence Vandromme, Miwako Tsuji

We implement a post-variational quantum neural network on a real HPC-QC system and show the feasibility of fully training this class of algorithms on current Noisy Intermediate-Scale Quantum (NISQ) devices, which are limited by noise, low number of qubits, and scarcity. Post-variational methods are hybrid classical-quantum Machine Learning algorithms that remove the need for quantum circuits evaluations during training, thus making them more suited to the availability constraints of physical quantum devices. We investigate the scalability of the algorithm to a higher number of qubits, larger datasets, and more elaborate models, giving insight for more efficient implementation. Experiments for an image classification task on a cutting-edge HPC-QC system show that post-variational quantum neural networks are fully trainable in reasonable times on a superconducting device. The models trained also show performance at least comparable to a variational approach, with one configuration showing a significant improvement in classification accuracy.

International Conference for High Performance Computing, Networking, Storage and Analysis (SC)•Nov 7, 2025•3 citations

Intelligent Search Strategies for Designing Robust Variational Quantum Models

Asha V, M T Vasumathi, Arpana Prasad +3 more

The use of Variational Quantum Circuits (VQCs), which are an important type of model in Quantum Machine Learning (QML) that will be used with Basic Quantum Computers during their Noisy intermediate-scale quantum (NISQ) era, is very dependent on the properties of the circuits themselves (architectures) and how they are trained (training settings). In fact, this model is so dependent on the knowledge of the human designer that creating these models takes significant time and energy to develop properly through qualitatively high amounts of quantum knowledge. In this work, we propose a new method for automatically building and training quantum machine learning models using an AutoML-Assisted approach to optimize VQCs. The overall goal of the AutoML-Assisted approach is to treat the design of quantum circuits as a learning problem and utilize Neural Architecture Search ( NAS ) to search end to end on the architecture, variational parameters, and hyperparameters automatically. Our experimental results on classification tasks show that the automatically learned VQCs not only give better accuracy but also give faster convergence and generally are more robust to quantum noise than warehouse VQCs developed by humans. This work makes a direct contribution to increasing the automation and scalability by which quantum machine learning can be run on NISQ computers.

International Conference on Smart Electronic Devices and Intelligent Systems (ICSEDIS)•Apr 13, 2026•0 citations
Variational quantum circuits (VQCs) have become a powerful tool for implementing Quantum Neural Networks (QNNs), addressing a wide range of complex problems. Well-trained VQCs serve as valuable intellectual assets hosted on cloud-based Noisy Intermediate Scale Quantum (NISQ) computers, making them susceptible to malicious VQC stealing attacks. However, traditional model extraction techniques designed for classical machine learning models encounter challenges when applied to NISQ computers due to significant noise in current devices. In this paper, we introduce QuantumLeak, an effective and accurate QNN model extraction technique from cloud-based NISQ machines. Compared to existing classical model stealing techniques, QuantumLeak improves local VQC accuracy by 4.99%~7.35% across diverse datasets and VQC architectures.
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 over-looked 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 90×, with only a modest increase in hardware overhead.
The recent success of Quantum Neural Networks (QNNs) prompts model extraction attacks on cloud platforms, even under black-box constraints. These attacks repeatedly query the victim QNN with malicious inputs. However, existing extraction attacks tailored for classical models yield local substitute QNNs with limited performance due to NISQ computer noise. Drawing from bagging-based ensemble learning, which uses independent weak learners to learn from noisy data, we introduce a novel QNN extraction approach. Our experimental results show this quantum ensemble learning approach improves local QNN accuracy by up to 15.09% compared to previous techniques.
Cloud hosting of quantum machine learning (QML) models exposes them to a range of vulnerabilities, the most significant of which is the model stealing attack. In this study, we assess the efficacy of such attacks in the realm of quantum computing. Our findings revealed that model stealing attacks can produce clone models achieving up to 0.9 × and 0.99 × clone test accuracy when trained using Top-1 and Top-k labels, respectively (k: num_classes). To defend against these attacks, we propose: 1) hardware variation-induced perturbation (HVIP) and 2) hardware and architecture variation-induced perturbation (HAVIP). Despite limited success with our defense techniques, it has led to an important discovery: QML models trained on noisy hardwares are naturally resistant to perturbation or obfuscation-based defenses or attacks.
With the evolution of technology, the need to solve complex computational problems like machine learning and deep learning has shot up. However, even the most powerful classical supercomputers find it difficult to execute these tasks. Advancements in quantum computing are leading researchers and tech-giants who strive for better quantum circuits to do machine learning tasks. Current works on Quantum Machine Learning (QML) ensure less memory consumption and reduced model parameters. However, it is strenuous to simulate the classical deep learning approach on existing quantum computing devices due to the inflexibility of Deep quantum circuits. Consequently, designing viable quantum algorithms for QML for noisy intermediate-scale quantum (NISQ) devices is essential. The proposed work aims to explore Variational Quantum Circuits (VQC) for Deep Q network-based Reinforcement Learning by remodeling the target network and experience replay into a representation of VQC. In addition, to the reduction in model parameters, quantum information encoding schemes are used to achieve better results than classical neural networks. VQCs are employed for policyselection and decision-making reinforcement learning by approximating the deep Q-value function with target network and experience replay.
We implement a post-variational quantum neural network on a real HPC-QC system and show the feasibility of fully training this class of algorithms on current Noisy Intermediate-Scale Quantum (NISQ) devices, which are limited by noise, low number of qubits, and scarcity. Post-variational methods are hybrid classical-quantum Machine Learning algorithms that remove the need for quantum circuits evaluations during training, thus making them more suited to the availability constraints of physical quantum devices. We investigate the scalability of the algorithm to a higher number of qubits, larger datasets, and more elaborate models, giving insight for more efficient implementation. Experiments for an image classification task on a cutting-edge HPC-QC system show that post-variational quantum neural networks are fully trainable in reasonable times on a superconducting device. The models trained also show performance at least comparable to a variational approach, with one configuration showing a significant improvement in classification accuracy.
The use of Variational Quantum Circuits (VQCs), which are an important type of model in Quantum Machine Learning (QML) that will be used with Basic Quantum Computers during their Noisy intermediate-scale quantum (NISQ) era, is very dependent on the properties of the circuits themselves (architectures) and how they are trained (training settings). In fact, this model is so dependent on the knowledge of the human designer that creating these models takes significant time and energy to develop properly through qualitatively high amounts of quantum knowledge. In this work, we propose a new method for automatically building and training quantum machine learning models using an AutoML-Assisted approach to optimize VQCs. The overall goal of the AutoML-Assisted approach is to treat the design of quantum circuits as a learning problem and utilize Neural Architecture Search ( NAS ) to search end to end on the architecture, variational parameters, and hyperparameters automatically. Our experimental results on classification tasks show that the automatically learned VQCs not only give better accuracy but also give faster convergence and generally are more robust to quantum noise than warehouse VQCs developed by humans. This work makes a direct contribution to increasing the automation and scalability by which quantum machine learning can be run on NISQ computers.