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:2402.11687 · ACM Great Lakes Symposium on VLSI (GLSVLSI)

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

Satwik Kundu, Debarshi Kundu, Swaroop Ghosh

Published Jun 10, 2024• 11 citations
arXivHTMLPDF

Abstract

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.

DOI
10.1145/3649476.3658806

Related papers

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

Zhenxiao Fu, Min Yang, Cheng Chu +3 more

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.

arXiv:2403.10790•International Joint Conference on Neural Networks (IJCNN)•Jun 30, 2024•13 citations

Quantum Quandaries: Unraveling Encoding Vulnerabilities in Quantum Neural Networks

Suryansh Upadhyay, Swaroop Ghosh

Quantum computing (QC) has the potential to revolutionize fields like machine learning, security, and healthcare. Quantum machine learning (QML) has emerged as a promising area, enhancing learning algorithms using quantum computers. However, QML models are lucrative targets due to their high training costs and extensive training times. The scarcity of quantum resources and long wait times further exacerbate the challenge. Additionally, QML providers may rely on third-party quantum clouds for hosting models, exposing them and their training data to potential threats. As QML-as-a-Service (QMLaaS) becomes more prevalent, reliance on third-party quantum clouds poses a significant security risk. This work demonstrates that adversaries in quantum cloud environments can exploit white-box access to QML models to infer the user's encoding scheme by analyzing circuit transpilation artifacts. The extracted data can be reused for training clone models or sold for profit. We validate the proposed attack through simulations, achieving high accuracy in distinguishing between encoding schemes. We report that ≈95% of the time, the encoding can be predicted correctly. To mitigate this threat, we propose a transient obfuscation layer that masks encoding fingerprints using randomized rotations and entanglement, reducing adversarial detection to near-random chance ≈42%, with a depth overhead of ≈8.5% for a 5-layer QNN design.

arXiv:2502.01486•International Symposium on Quality Electronic Design (ISQED)•Apr 23, 2025•8 citations

Towards Robust Quantum Machine Learning

Saeefa Rubaiyet Nowmi, Jesus Lopez, Md Mahmudul Alam Imon +3 more

Quantum Machine Learning (QML) fuses quantum computing with machine learning to address complex tasks with potential speedups over classical methods. While QML models such as variational quantum classifiers (QVC), quantum multilayer perceptron(QMLP) models and quantum convolutional neural networks (QCNN) have demonstrated promise in applications like image recognition and malware classification, they remain vulnerable to adversarial threats. Inspired by the vulnerabilities in classical ML, this work systematically investigates how attacks-ranging from training-time poisoning and inferencetime evasion (e.g., quantum versions of FGSM and PGD) to deployment-time trigger attacks-manifest in quantum circuits. We explore how classical adversarial strategies adapt to quantum models through parameterized encodings, hybrid architectures, and probabilistic outputs. The poster evaluates different quantum classifiers under adversarial settings, comparing their robustness, trainability, and resilience to perturbations. Defense mechanisms such as randomized encoding, engineered noise channels, and quantum adversarial training are analyzed in relation to specific threat types. In addition, we assess how quantum models behave differently than classical counterparts under attack, and how quantum-specific design constraints can either exacerbate or mitigate these effects. Our ultimate goal is to define and construct robust QML systems that are both theoretically sound and practically secure. By synthesizing results across multiple QML architectures and threat models, this work provides actionable insight into the development of resilient quantum classifiers, paving the way toward trustworthy and scalable quantum machine learning.

IEEE International Conference on Quantum Computing and Engineering (QCE)•Aug 30, 2025•2 citations

The Quantum Imitation Game: Reverse Engineering of Quantum Machine Learning Models

Archisman Ghosh, Swaroop Ghosh

Quantum Machine Learning (QML) is an amalgamation of quantum computing paradigms with machine learning models, providing significant prospects for solving complex problems. However, with the expansion of numerous third-party vendors in the Noisy Intermediate-Scale Quantum (NISQ) era of quantum computing, the security of QML models is of prime importance, particularly against reverse engineering, which could expose sensitive parameters and proprietary algorithms embedded within the models. We assume the untrusted third-party quantum cloud provider is an adversary having white-box access to the transpiled version of the user-designed trained QML model during inference. Although the adversary can steal and use the model without any modification, reverse engineering (RE) to extract the pre-transpiled copy of the QML circuit will enable re-transpilation and usage of the model for various hardware with completely different native gate sets and even different qubit technology. The information about the parameters (e.g., number of parameters, their placements, and optimized values) can allow further training of the QML model if the adversary plans to alter the QML model to tamper with the watermark and/or embed their own watermark or refine the model for other purposes. In this first effort to investigate the RE of QML circuits, we examine quantum classifiers by comparing the training accuracy of original and reverse-engineered models across various sizes (i.e., number of qubits and number of parametric layers) of Quantum Neural Networks (QNNs). We note that multi-qubit classifiers can be reverse-engineered under specific conditions with a mean error of order 10^-2 in a reasonable time. We also propose adding dummy rotation gates in the QML model with fixed parameters to increase the RE overhead for defense. For instance, an addition of 2 dummy qubits and 2 layers increases the overhead by ~1.76 times for a classifier with 2 qubits and 3 layers with a performance overhead of less than 9%. We note that RE is a very powerful attack model which warrants further efforts on defenses.

arXiv:2407.07237•Workshop on Attacks and Solutions in Hardware Security (ASHES)•Nov 19, 2024•11 citations

Quantum Data Breach: Reusing Training Dataset by Untrusted Quantum Clouds

Suryansh Upadhyay, Swaroop Ghosh

Quantum computing (QC) has the potential to rev-olutionize fields like machine learning, security, and healthcare. Quantum machine learning (QML) has emerged as a promising area, enhancing learning algorithms using quantum computers. However, QML models are lucrative targets due to their high training costs and extensive training times. The scarcity of quantum resources and long wait times further exacerbate the challenge. Additionally, QML providers may rely on a third-party quantum cloud for hosting the model, exposing the models and training data. As QML-as-a-Service (QMLaaS) becomes more prevalent, reliance on third party quantum clouds can pose a significant threat. This paper shows that adversaries in quantum clouds can use white-box access of the QML model during training to extract the state preparation circuit (containing training data) along with the labels. The extracted training data can be reused for training a clone model or sold for profit. We propose a suite of techniques to prune and fix the incorrect labels. Results show that ≈90% labels can be extracted correctly. The same model trained on the adversarially extracted data achieves approximately ≈90% accuracy, closely matching the accuracy achieved when trained on the original data. To mitigate this threat, we propose masking labels/classes and modifying the cost function for label obfuscation, reducing adversarial label prediction accuracy by ≈70%.

arXiv:2407.14687•International Symposium on Quality Electronic Design (ISQED)•Apr 23, 2025•5 citations

Defending Quantum Classifiers against Adversarial Perturbations through Quantum Autoencoders

Emma Andrews, Sahan Sanjaya, Prabhat Mishra

Machine learning models can learn from data samples to carry out various tasks efficiently. When data samples are adversarially manipulated, such as by insertion of carefully crafted noise, it can cause the model to make mistakes. Quantum machine learning models are also vulnerable to such adversarial attacks, especially in image classification using variational quantum classifiers. While there are promising defenses against these adversarial perturbations, such as training with adversarial samples, they face practical limitations. For example, they are not applicable in scenarios where training with adversarial samples is either not possible or can overfit the models on one type of attack. In this paper, we propose an adversarial training-free defense framework that utilizes a quantum autoencoder to purify the adversarial samples through reconstruction. Moreover, our defense framework provides a confidence metric to identify potentially adversarial samples that cannot be purified the quantum autoencoder. Extensive evaluation demonstrates that our defense framework can significantly outperform state-of-the-art in prediction accuracy (up to 68%) under adversarial attacks.

quant-pharXiv:2604.28176•May 1, 2026•0 citations
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.
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 computing (QC) has the potential to revolutionize fields like machine learning, security, and healthcare. Quantum machine learning (QML) has emerged as a promising area, enhancing learning algorithms using quantum computers. However, QML models are lucrative targets due to their high training costs and extensive training times. The scarcity of quantum resources and long wait times further exacerbate the challenge. Additionally, QML providers may rely on third-party quantum clouds for hosting models, exposing them and their training data to potential threats. As QML-as-a-Service (QMLaaS) becomes more prevalent, reliance on third-party quantum clouds poses a significant security risk. This work demonstrates that adversaries in quantum cloud environments can exploit white-box access to QML models to infer the user's encoding scheme by analyzing circuit transpilation artifacts. The extracted data can be reused for training clone models or sold for profit. We validate the proposed attack through simulations, achieving high accuracy in distinguishing between encoding schemes. We report that ≈95% of the time, the encoding can be predicted correctly. To mitigate this threat, we propose a transient obfuscation layer that masks encoding fingerprints using randomized rotations and entanglement, reducing adversarial detection to near-random chance ≈42%, with a depth overhead of ≈8.5% for a 5-layer QNN design.
Quantum Machine Learning (QML) fuses quantum computing with machine learning to address complex tasks with potential speedups over classical methods. While QML models such as variational quantum classifiers (QVC), quantum multilayer perceptron(QMLP) models and quantum convolutional neural networks (QCNN) have demonstrated promise in applications like image recognition and malware classification, they remain vulnerable to adversarial threats. Inspired by the vulnerabilities in classical ML, this work systematically investigates how attacks-ranging from training-time poisoning and inferencetime evasion (e.g., quantum versions of FGSM and PGD) to deployment-time trigger attacks-manifest in quantum circuits. We explore how classical adversarial strategies adapt to quantum models through parameterized encodings, hybrid architectures, and probabilistic outputs. The poster evaluates different quantum classifiers under adversarial settings, comparing their robustness, trainability, and resilience to perturbations. Defense mechanisms such as randomized encoding, engineered noise channels, and quantum adversarial training are analyzed in relation to specific threat types. In addition, we assess how quantum models behave differently than classical counterparts under attack, and how quantum-specific design constraints can either exacerbate or mitigate these effects. Our ultimate goal is to define and construct robust QML systems that are both theoretically sound and practically secure. By synthesizing results across multiple QML architectures and threat models, this work provides actionable insight into the development of resilient quantum classifiers, paving the way toward trustworthy and scalable quantum machine learning.
Quantum Machine Learning (QML) is an amalgamation of quantum computing paradigms with machine learning models, providing significant prospects for solving complex problems. However, with the expansion of numerous third-party vendors in the Noisy Intermediate-Scale Quantum (NISQ) era of quantum computing, the security of QML models is of prime importance, particularly against reverse engineering, which could expose sensitive parameters and proprietary algorithms embedded within the models. We assume the untrusted third-party quantum cloud provider is an adversary having white-box access to the transpiled version of the user-designed trained QML model during inference. Although the adversary can steal and use the model without any modification, reverse engineering (RE) to extract the pre-transpiled copy of the QML circuit will enable re-transpilation and usage of the model for various hardware with completely different native gate sets and even different qubit technology. The information about the parameters (e.g., number of parameters, their placements, and optimized values) can allow further training of the QML model if the adversary plans to alter the QML model to tamper with the watermark and/or embed their own watermark or refine the model for other purposes. In this first effort to investigate the RE of QML circuits, we examine quantum classifiers by comparing the training accuracy of original and reverse-engineered models across various sizes (i.e., number of qubits and number of parametric layers) of Quantum Neural Networks (QNNs). We note that multi-qubit classifiers can be reverse-engineered under specific conditions with a mean error of order 10^-2 in a reasonable time. We also propose adding dummy rotation gates in the QML model with fixed parameters to increase the RE overhead for defense. For instance, an addition of 2 dummy qubits and 2 layers increases the overhead by ~1.76 times for a classifier with 2 qubits and 3 layers with a performance overhead of less than 9%. We note that RE is a very powerful attack model which warrants further efforts on defenses.
Quantum computing (QC) has the potential to rev-olutionize fields like machine learning, security, and healthcare. Quantum machine learning (QML) has emerged as a promising area, enhancing learning algorithms using quantum computers. However, QML models are lucrative targets due to their high training costs and extensive training times. The scarcity of quantum resources and long wait times further exacerbate the challenge. Additionally, QML providers may rely on a third-party quantum cloud for hosting the model, exposing the models and training data. As QML-as-a-Service (QMLaaS) becomes more prevalent, reliance on third party quantum clouds can pose a significant threat. This paper shows that adversaries in quantum clouds can use white-box access of the QML model during training to extract the state preparation circuit (containing training data) along with the labels. The extracted training data can be reused for training a clone model or sold for profit. We propose a suite of techniques to prune and fix the incorrect labels. Results show that ≈90% labels can be extracted correctly. The same model trained on the adversarially extracted data achieves approximately ≈90% accuracy, closely matching the accuracy achieved when trained on the original data. To mitigate this threat, we propose masking labels/classes and modifying the cost function for label obfuscation, reducing adversarial label prediction accuracy by ≈70%.
Machine learning models can learn from data samples to carry out various tasks efficiently. When data samples are adversarially manipulated, such as by insertion of carefully crafted noise, it can cause the model to make mistakes. Quantum machine learning models are also vulnerable to such adversarial attacks, especially in image classification using variational quantum classifiers. While there are promising defenses against these adversarial perturbations, such as training with adversarial samples, they face practical limitations. For example, they are not applicable in scenarios where training with adversarial samples is either not possible or can overfit the models on one type of attack. In this paper, we propose an adversarial training-free defense framework that utilizes a quantum autoencoder to purify the adversarial samples through reconstruction. Moreover, our defense framework provides a confidence metric to identify potentially adversarial samples that cannot be purified the quantum autoencoder. Extensive evaluation demonstrates that our defense framework can significantly outperform state-of-the-art in prediction accuracy (up to 68%) under adversarial attacks.