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

Control Instrumentation System Conference (CISCON)

Improved Quantum Neural Network for Intrusion Detection and Blowfish for Data Security

B. N. Nithya, Sailaja Bhaskar Murthy, Samudyatha DS

Published Aug 1, 2025• 1 citation
Publisher
DOI
10.1109/ciscon66933.2025.11337273

Related papers

Hybrid Quantum-Classical Neural Networks for Network Intrusion Detection: A Parameter-Efficient Approach

Taha-Amine Miri, Aissa Kerkour Elmiad, Aziz Oukaira +1 more

Lecture notes in networks and systems•Jan 1, 2026•0 citations

Leveraging Quantum Computing for Improved Intrusion Detection and Security Analytics: A Survey

Suman Bijapur, Sudhir Anakal

International Conference on Intelligent Methods and Advanced Computer Scientific Innovations (IMACSI)•Jan 1, 2025•0 citations

Full-Rotation Quantum Convolutional Neural Network for Abnormal Intrusion Detection System

Suya Chao, Guang Yang, Min Nie +2 more

Intrusion detection system (IDS) is a significant mechanism to improve network security. As a promising technique, machine learning (ML) methods has been applied in IDS to obtain high classification accuracy. However, classical ML based IDS methods hit a bottleneck in computing performance in case of huge network traffic and complex high-dimensional data. Due to the parallelism, superposition, entanglement of quantum computing, quantum computing provides a new solution to speed up the classical ML algorithms. This paper proposes a novel IDS scheme based on full-rotation quantum convolutional neural network (FR-QCNN). The key component of the FR-QCNN is the quantum convolution filter, which is composed of coding layer, variational layer and measurement layer. Different from the traditional quantum convolutional neural network, a full-rotation quantum circuit is used in the variational layer of the FR-QCNN, realizing a complete parameter update in the model training. Experiment on dataset from KDD Cup shows that the IDS classification accuracy of FR-QCNN is higher than classical ML models such as convolutional neural network (CNN), decision tree (DT) and support vector machine (SVM), as well as higher than traditional quantum convolutional neural network(QCNN). Meanwhile, FR-QCNN and QCNN have lower space complexity and time complexity than classical ML methods.

•Sep 23, 2022•4 citations

Quantum Neural Networks Under Threat: Modeling Security Risks and Attack Vectors

Nouhaila Innan, Walid El Maouaki, Alberto Marchisio +1 more

Communications in computer and information science•Jan 1, 2026•1 citation

Federated Quantum Generative Adversarial Network for Intrusion Detection

Franco Cirillo, Christian Esposito

In increasingly complex digital environments, Intrusion Detection Systems (IDS) are essential for maintaining network security. Traditional machine learning techniques face challenges, including difficulties with high-dimensional data and performance issues when dealing with unbalanced datasets. Although Generative Adversarial Networks (GANs) provide an acceptable alternative by improving data creation, their traditional implementations are computationally demanding and have limitations when it comes to examining intricate data distributions. Quantum GANs (QGANs) use the benefits of quantum computing to solve these problems. Therefore, a distributed approach improves load balancing and mitigate the impact of quantum noise for NISQ devices. The proposed model efficiently learns the distribution of benign data by employing a federated hybrid QGAN architecture that combines a quantum generators with a classical discriminators. This allows the model to produce samples that closely mimic patterns found in real data. The generator in the proposed QGAN is a variational quantum circuit (VQC), and the discriminator is a neural network. Tested on the NSL-KDD dataset, the federated QGAN offers a promising option for next-generation IDS.

IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW)•Jul 21, 2025•2 citations

Quantum Machine Learning-Based Intrusion Detection: A Comparative Study on Real Quantum Hardware

Attila Balázs Nagy, Yue Wu, Ács Szilvia +2 more

Quantum Machine Learning (QML) has become a promising alternative in the field of network anomaly detection (NAD) in recent years, especially in intrusion detection. in the development of intrusion detection systems (IDS). The aim of this study is to examine in detail four quantum machine learning models that were run not on simulators but on real quantum computers, including IBM QPU and IonQ Aria-1 platforms. The analyzed research uses different architectures, such as Quantum Convolutional Neural Network (QCNN), Variational Quantum Classifier (VQC), Quantum Autoencoder (QAE) and Quantum Neural Network (QNN), combined with multiple data processing methods and encoding techniques.

IEEE International Symposium on Intelligent Systems and Informatics (SISY)•Sep 25, 2025•1 citation
Intrusion detection system (IDS) is a significant mechanism to improve network security. As a promising technique, machine learning (ML) methods has been applied in IDS to obtain high classification accuracy. However, classical ML based IDS methods hit a bottleneck in computing performance in case of huge network traffic and complex high-dimensional data. Due to the parallelism, superposition, entanglement of quantum computing, quantum computing provides a new solution to speed up the classical ML algorithms. This paper proposes a novel IDS scheme based on full-rotation quantum convolutional neural network (FR-QCNN). The key component of the FR-QCNN is the quantum convolution filter, which is composed of coding layer, variational layer and measurement layer. Different from the traditional quantum convolutional neural network, a full-rotation quantum circuit is used in the variational layer of the FR-QCNN, realizing a complete parameter update in the model training. Experiment on dataset from KDD Cup shows that the IDS classification accuracy of FR-QCNN is higher than classical ML models such as convolutional neural network (CNN), decision tree (DT) and support vector machine (SVM), as well as higher than traditional quantum convolutional neural network(QCNN). Meanwhile, FR-QCNN and QCNN have lower space complexity and time complexity than classical ML methods.
In increasingly complex digital environments, Intrusion Detection Systems (IDS) are essential for maintaining network security. Traditional machine learning techniques face challenges, including difficulties with high-dimensional data and performance issues when dealing with unbalanced datasets. Although Generative Adversarial Networks (GANs) provide an acceptable alternative by improving data creation, their traditional implementations are computationally demanding and have limitations when it comes to examining intricate data distributions. Quantum GANs (QGANs) use the benefits of quantum computing to solve these problems. Therefore, a distributed approach improves load balancing and mitigate the impact of quantum noise for NISQ devices. The proposed model efficiently learns the distribution of benign data by employing a federated hybrid QGAN architecture that combines a quantum generators with a classical discriminators. This allows the model to produce samples that closely mimic patterns found in real data. The generator in the proposed QGAN is a variational quantum circuit (VQC), and the discriminator is a neural network. Tested on the NSL-KDD dataset, the federated QGAN offers a promising option for next-generation IDS.
Quantum Machine Learning (QML) has become a promising alternative in the field of network anomaly detection (NAD) in recent years, especially in intrusion detection. in the development of intrusion detection systems (IDS). The aim of this study is to examine in detail four quantum machine learning models that were run not on simulators but on real quantum computers, including IBM QPU and IonQ Aria-1 platforms. The analyzed research uses different architectures, such as Quantum Convolutional Neural Network (QCNN), Variational Quantum Classifier (VQC), Quantum Autoencoder (QAE) and Quantum Neural Network (QNN), combined with multiple data processing methods and encoding techniques.