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:2411.11870 · Advanced Quantum Technologies

Designing Robust Quantum Neural Networks via Optimized Circuit Metrics

Walid El Maouaki, Alberto Marchisio, Taoufik Said, Muhammad Shafique, Mohamed Bennai

Published Mar 17, 2025• 17 citations
arXivHTMLPDF

Abstract

Abstract In this study, the robustness of Quanvolutional Neural Networks (QuNNs) is investigated in comparison to their classical counterparts, Convolutional Neural Networks (CNNs), against two adversarial attacks: the Fast Gradient Sign Method (FGSM) and the Projected Gradient Descent (PGD), for the image classification task on both the Modified National Institute of Standards and Technology (MNIST) and Fashion‐MNIST (FMNIST) datasets. To enhance the robustness of QuNNs, a novel methodology is developed that utilizes three quantum circuit metrics: expressibility, entanglement capability, and controlled rotation gate selection. This analysis shows that these metrics significantly influence data representation within the Hilbert space, thereby directly affecting QuNN robustness. It is rigorously established that circuits with higher expressibility and lower entanglement capability generally exhibit enhanced robustness under adversarial conditions, particularly at low‐spectrum perturbation strengths where most attacks occur. Furthermore, these findings challenge the prevailing assumption that expressibility alone dictates circuit robustness; instead, it is demonstrated that the inclusion of controlled rotation gates around the Z‐axis generally enhances the resilience of QuNNs. These results demonstrate that QuNNs exhibit up to 60% greater robustness on the MNIST dataset and 40% on the Fashion‐MNIST dataset compared to CNNs. Collectively, this work elucidates the relationship between quantum circuit metrics and robust data feature extraction, advancing the field by improving the adversarial robustness of QuNNs.

DOI
10.1002/qute.202400601

Related papers

RobQuNNs: A Methodology for Robust Quanvolutional Neural Networks against Adversarial Attacks

Walid El Maouaki, Alberto Marchisio, Taoufik Said +2 more

Recent advancements in quantum computing have led to the emergence of hybrid quantum neural networks, such as Quanvolutional Neural Networks (QuNNs), which integrate quantum and classical layers. While the susceptibility of classical neural networks to adversarial attacks is well-documented, the impact on QuNNs remains less understood. This study introduces RobQuNN, a new methodology to enhance the robustness of QuNNs against adversarial attacks, utilizing quantum circuit expressibility and entanglement capability alongside different adversarial strategies. Additionally, the study investigates the transferability of adversarial examples between classical and quantum models using RobQuNN, enhancing our understanding of cross-model vulnerabilities and pointing to new directions in quantum cybersecurity. The findings reveal that QuNNs exhibit up to 60% higher robustness compared to classical networks for the MNIST dataset, particularly at low levels of perturbation. This underscores the potential of quantum approaches in improving security defenses. In addition, RobQuNN revealed that QuNN does not exhibit enhanced resistance or susceptibility to cross-model adversarial examples regardless of the quantum circuit architecture.

arXiv:2407.03875•IEEE International Conference on Image Processing Workshops (ICIPW)•Oct 27, 2024•9 citations

AdvQuNN: A Methodology for Analyzing the Adversarial Robustness of Quanvolutional Neural Networks

Walid El Maouaki, Alberto Marchisio, Taoufik Said +2 more

Recent advancements in quantum computing have led to the development of hybrid quantum neural networks (HQNNs) that employ a mixed set of quantum layers and classical layers, such as Quanvolutional Neural Networks (QuNNs). While several works have shown security threats of classical neural networks, such as adversarial attacks, their impact on QuNNs is still relatively unexplored. This work tackles this problem by designing AdvQuNN, a specialized methodology to investigate the robustness of HQNNs like QuNNs against adversarial attacks. It employs different types of Ansatzes as parametrized quantum circuits and different types of adversarial attacks. This study aims to rigorously assess the influence of quantum circuit architecture on the resilience of QuNN models, which opens up new pathways for enhancing the robustness of QuNNs and advancing the field of quantum cybersecurity. Our results show that, compared to classical convolutional networks, QuNNs achieve up to 60% higher robustness for the MNIST and 40% for FMNIST datasets.

arXiv:2403.05596•IEEE International Conference on Quantum Software (QSW)•Jul 7, 2024•21 citations

A Parallel Hybrid Quantum‐Classical Convolutional Design Using Parameterized Quantum Circuits for Image Classification

Haoxuan Liu, Xiaoping Lou

Image classification plays a critical role across various industries, yet the rapid growth of visual data has significantly increased computational complexity. Convolutional neural networks (CNNs) have demonstrated strong capabilities in efficient feature extraction, but they still face trade‐offs between performance and computational cost when handling large‐scale data. Recent studies have explored integrating quantum mechanical principles into classical CNNs to enhance model expressivity. However, existing hybrid quantum–classical convolutional architectures remain limited in terms of feature capture and computational efficiency. In this study, we propose a novel hybrid quantum–classical convolutional neural network (QC‐CNN‐Parallel), which introduces parallel quantum and classical convolutional branches and extends the concept of multiscale convolution to hybrid networks. This design enables the capture of larger contextual information during convolution while reducing circuit depth and computational overhead. Moreover, we employ parameterized quantum circuits (PQCs) with expressibility, entanglement, and discreteness metrics to select optimal quantum circuits and further enhance model performance. We evaluate QC‐CNN‐Parallel on three grayscale image datasets: MNIST, Fashion‐MNIST, and Overhead‐MNIST. Experimental results show that our model improves average training accuracy by 4.89%, 2.77%, and 6.24% over existing hybrid quantum CNNs and classical CNNs, respectively, while exhibiting superior robustness. These results demonstrate that QC‐CNN‐Parallel achieves enhanced classification performance with high computational efficiency and practical potential.

Quantum Engineering•Jan 1, 2026•3 citations

Adversarial Robustness of Hybrid Quantum Convolutional Neural Networks in Medical Image Analysis

Τheofanis Kalampokas, Εleni Vrochidou, George A. Papakostas

In this work, we investigate the performance of hybrid quantum-classical convolutional neural networks (QCNNs) in medical image classification under the presence of adversarial attacks. Adversarial attacks pose a significant threat to image classification models, since they introduce subtle perturbations to input images, leading to incorrect predictions. Specifically, in this work, 10 QCNNs with their corresponding classic Convolutional Neural Networks (CNNs) counterparts are comparatively examined for their robustness, on two different medical image datasets using transfer learning, under two different adversarial attacks. In a subsequent step, the implementation of training models from scratch is also evaluated. With transfer learning on the X-ray dataset, CNN and QCNN models achieve high and comparable performance across most backbones. On the histopathological dataset, CNNs and QCNNs often generalize worse compared to the X-ray dataset, indicating head overfitting under domain shift. The adversarial evaluation results highlight that most models' robustness comes from the backbone rather than the head. QCNN models perform comparably to CNNs under attack and show improvements when trained from scratch. Overall, the results indicate that integrating quantum circuit mechanisms into classical CNN architectures can enhance the robustness of models in medical imaging tasks, representing a promising domain that warrants further investigation.

CRC Press eBooks•Sep 10, 2026•0 citations

Classical-Quantum CNN Hybrid for Image Classification

Muhamad Akrom, Wahyu Aji Eko Prabowo

This study explores Quantum Convolutional Neural Network (QCNN) starting from foundational quantum operations, such as the Rx gate for encoding MNIST image data into quantum states. We implemented quantum convolutional and pooling layers using one_unitary and two_unitary circuits, enabling effective feature extraction and dimensionality reduction while preserving critical information. Expressibility analysis revealed varying capabilities across different one_unitary circuits, with Rx, Ry, and Rz combinations demonstrating promising results akin to Haar random states. The proposed QCNN model exhibited robust performance metrics (accuracy: 95.98%, precision: 94.44%, recall: 96.59%, F1-score: 0.9551, AUC: 0.9604) in classification tasks, supported by efficient convergence during optimization. Future directions include expanding QCNN applications to handle more complex datasets and optimizing architectures to enhance quantum machine learning capabilities, particularly in image processing. This study underscores the potential of QCNNs in advancing quantum computing applications in neural network architectures. Keywords: MNIST, classification, CNN, expressibility

Techno Com•Nov 18, 2019•0 citations

Formation Models of Technical Terms in English, Uzbek And Russian

Abdullayeva Fotima Bakhromovna

The integration of quantum computing principles with classical deep learning architectures has emerged as a promising direction for advancing image recognition systems beyond the limitations of purely classical convolutional neural networks (CNNs). This study proposes and analyzes a hybrid quantum–classical deep learning framework based on quanvolutional neural network (QNN) principles, where quantum circuits are embedded within convolutional feature extraction layers to enhance representation capability. The research investigates how quantum-enhanced filters, particularly quanvolutional layers, contribute to improved feature diversity, non-linear transformation capacity, and classification accuracy in image recognition tasks. Building upon established convolutional architectures and quantum machine learning theories, the proposed framework integrates quantum random circuit encoding with classical deep neural networks to evaluate performance gains in comparison to conventional CNN models. The study further incorporates theoretical insights from hybrid quantum-classical learning systems, emphasizing the role of parameterized quantum circuits in feature mapping and optimization stability. The methodology is grounded in NISQ-era quantum computing constraints and leverages hybrid optimization strategies to ensure computational feasibility. Experimental evaluation demonstrates that quanvolution-based models can provide improved robustness in feature extraction, particularly in high-dimensional image spaces, while maintaining competitive computational efficiency. However, scalability limitations and noise sensitivity in quantum circuits remain key challenges. Overall, this work contributes to the growing field of quantum-enhanced machine learning by providing a structured performance analysis of hybrid quanvolutional architectures and highlighting their potential role in next-generation intelligent visual recognition systems.

American Journal Of Philological Sciences•May 31, 2026•0 citations
Abstract In this study, the robustness of Quanvolutional Neural Networks (QuNNs) is investigated in comparison to their classical counterparts, Convolutional Neural Networks (CNNs), against two adversarial attacks: the Fast Gradient Sign Method (FGSM) and the Projected Gradient Descent (PGD), for the image classification task on both the Modified National Institute of Standards and Technology (MNIST) and Fashion‐MNIST (FMNIST) datasets. To enhance the robustness of QuNNs, a novel methodology is developed that utilizes three quantum circuit metrics: expressibility, entanglement capability, and controlled rotation gate selection. This analysis shows that these metrics significantly influence data representation within the Hilbert space, thereby directly affecting QuNN robustness. It is rigorously established that circuits with higher expressibility and lower entanglement capability generally exhibit enhanced robustness under adversarial conditions, particularly at low‐spectrum perturbation strengths where most attacks occur. Furthermore, these findings challenge the prevailing assumption that expressibility alone dictates circuit robustness; instead, it is demonstrated that the inclusion of controlled rotation gates around the Z‐axis generally enhances the resilience of QuNNs. These results demonstrate that QuNNs exhibit up to 60% greater robustness on the MNIST dataset and 40% on the Fashion‐MNIST dataset compared to CNNs. Collectively, this work elucidates the relationship between quantum circuit metrics and robust data feature extraction, advancing the field by improving the adversarial robustness of QuNNs.
Recent advancements in quantum computing have led to the emergence of hybrid quantum neural networks, such as Quanvolutional Neural Networks (QuNNs), which integrate quantum and classical layers. While the susceptibility of classical neural networks to adversarial attacks is well-documented, the impact on QuNNs remains less understood. This study introduces RobQuNN, a new methodology to enhance the robustness of QuNNs against adversarial attacks, utilizing quantum circuit expressibility and entanglement capability alongside different adversarial strategies. Additionally, the study investigates the transferability of adversarial examples between classical and quantum models using RobQuNN, enhancing our understanding of cross-model vulnerabilities and pointing to new directions in quantum cybersecurity. The findings reveal that QuNNs exhibit up to 60% higher robustness compared to classical networks for the MNIST dataset, particularly at low levels of perturbation. This underscores the potential of quantum approaches in improving security defenses. In addition, RobQuNN revealed that QuNN does not exhibit enhanced resistance or susceptibility to cross-model adversarial examples regardless of the quantum circuit architecture.
Recent advancements in quantum computing have led to the development of hybrid quantum neural networks (HQNNs) that employ a mixed set of quantum layers and classical layers, such as Quanvolutional Neural Networks (QuNNs). While several works have shown security threats of classical neural networks, such as adversarial attacks, their impact on QuNNs is still relatively unexplored. This work tackles this problem by designing AdvQuNN, a specialized methodology to investigate the robustness of HQNNs like QuNNs against adversarial attacks. It employs different types of Ansatzes as parametrized quantum circuits and different types of adversarial attacks. This study aims to rigorously assess the influence of quantum circuit architecture on the resilience of QuNN models, which opens up new pathways for enhancing the robustness of QuNNs and advancing the field of quantum cybersecurity. Our results show that, compared to classical convolutional networks, QuNNs achieve up to 60% higher robustness for the MNIST and 40% for FMNIST datasets.
Image classification plays a critical role across various industries, yet the rapid growth of visual data has significantly increased computational complexity. Convolutional neural networks (CNNs) have demonstrated strong capabilities in efficient feature extraction, but they still face trade‐offs between performance and computational cost when handling large‐scale data. Recent studies have explored integrating quantum mechanical principles into classical CNNs to enhance model expressivity. However, existing hybrid quantum–classical convolutional architectures remain limited in terms of feature capture and computational efficiency. In this study, we propose a novel hybrid quantum–classical convolutional neural network (QC‐CNN‐Parallel), which introduces parallel quantum and classical convolutional branches and extends the concept of multiscale convolution to hybrid networks. This design enables the capture of larger contextual information during convolution while reducing circuit depth and computational overhead. Moreover, we employ parameterized quantum circuits (PQCs) with expressibility, entanglement, and discreteness metrics to select optimal quantum circuits and further enhance model performance. We evaluate QC‐CNN‐Parallel on three grayscale image datasets: MNIST, Fashion‐MNIST, and Overhead‐MNIST. Experimental results show that our model improves average training accuracy by 4.89%, 2.77%, and 6.24% over existing hybrid quantum CNNs and classical CNNs, respectively, while exhibiting superior robustness. These results demonstrate that QC‐CNN‐Parallel achieves enhanced classification performance with high computational efficiency and practical potential.
In this work, we investigate the performance of hybrid quantum-classical convolutional neural networks (QCNNs) in medical image classification under the presence of adversarial attacks. Adversarial attacks pose a significant threat to image classification models, since they introduce subtle perturbations to input images, leading to incorrect predictions. Specifically, in this work, 10 QCNNs with their corresponding classic Convolutional Neural Networks (CNNs) counterparts are comparatively examined for their robustness, on two different medical image datasets using transfer learning, under two different adversarial attacks. In a subsequent step, the implementation of training models from scratch is also evaluated. With transfer learning on the X-ray dataset, CNN and QCNN models achieve high and comparable performance across most backbones. On the histopathological dataset, CNNs and QCNNs often generalize worse compared to the X-ray dataset, indicating head overfitting under domain shift. The adversarial evaluation results highlight that most models' robustness comes from the backbone rather than the head. QCNN models perform comparably to CNNs under attack and show improvements when trained from scratch. Overall, the results indicate that integrating quantum circuit mechanisms into classical CNN architectures can enhance the robustness of models in medical imaging tasks, representing a promising domain that warrants further investigation.
This study explores Quantum Convolutional Neural Network (QCNN) starting from foundational quantum operations, such as the Rx gate for encoding MNIST image data into quantum states. We implemented quantum convolutional and pooling layers using one_unitary and two_unitary circuits, enabling effective feature extraction and dimensionality reduction while preserving critical information. Expressibility analysis revealed varying capabilities across different one_unitary circuits, with Rx, Ry, and Rz combinations demonstrating promising results akin to Haar random states. The proposed QCNN model exhibited robust performance metrics (accuracy: 95.98%, precision: 94.44%, recall: 96.59%, F1-score: 0.9551, AUC: 0.9604) in classification tasks, supported by efficient convergence during optimization. Future directions include expanding QCNN applications to handle more complex datasets and optimizing architectures to enhance quantum machine learning capabilities, particularly in image processing. This study underscores the potential of QCNNs in advancing quantum computing applications in neural network architectures. Keywords: MNIST, classification, CNN, expressibility
The integration of quantum computing principles with classical deep learning architectures has emerged as a promising direction for advancing image recognition systems beyond the limitations of purely classical convolutional neural networks (CNNs). This study proposes and analyzes a hybrid quantum–classical deep learning framework based on quanvolutional neural network (QNN) principles, where quantum circuits are embedded within convolutional feature extraction layers to enhance representation capability. The research investigates how quantum-enhanced filters, particularly quanvolutional layers, contribute to improved feature diversity, non-linear transformation capacity, and classification accuracy in image recognition tasks. Building upon established convolutional architectures and quantum machine learning theories, the proposed framework integrates quantum random circuit encoding with classical deep neural networks to evaluate performance gains in comparison to conventional CNN models. The study further incorporates theoretical insights from hybrid quantum-classical learning systems, emphasizing the role of parameterized quantum circuits in feature mapping and optimization stability. The methodology is grounded in NISQ-era quantum computing constraints and leverages hybrid optimization strategies to ensure computational feasibility. Experimental evaluation demonstrates that quanvolution-based models can provide improved robustness in feature extraction, particularly in high-dimensional image spaces, while maintaining competitive computational efficiency. However, scalability limitations and noise sensitivity in quantum circuits remain key challenges. Overall, this work contributes to the growing field of quantum-enhanced machine learning by providing a structured performance analysis of hybrid quanvolutional architectures and highlighting their potential role in next-generation intelligent visual recognition systems.