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

International Conference Computational Vision and Bio Inspired Computing

Hybrid Quantum Classical Deep Learning Model for Encrypted HTTPS Traffic Classification

V.Lakshmi chaitanya, B. Himaja, G vijaya Bhaskar, G Kiran Kumar, M. V. Subramanyam, K. Bhanu Murthy

Published Aug 1, 2026• 0 citations
Publisher

Abstract

As cyberattacks evolve in greater impact and complexity, they have Network traffic classification is a key component of any modern or intelligent cybersecurity system, which includes monitoring, managing network resources, detecting intrusions, and managing application-aware network operations. Unfortunately, with the complexity of networks increasing and ubiquitous use of encryption communication protocols, traditional traffic analysis methods were significantly diminished. To meet the challenges, a hybrid quantum-classical machine learning approach to the network traffic classification is proposed in this paper. The approach that is proposed in this paper utilizes the Dataset-Unicauca-Version2-87Atts, which originally contains approximately 3.57 million flow records. The experimental evaluation is performed on a balanced subset obtained after preprocessing and class balancing. To enhance the data quality and the capability to learn, a comprehensive preprocessing pipeline is employed, which contains feature selection, missing value handling, logarithmic data transformation, label encoding, and feature standardization. The whole effort combines a classical neural component with an angle embedding quantum circuit using strongly entangling quantum layers, all of which are assembled with PennyLane. The quantum layer processes four qubits and encodes network traffic patterns into multiple dimensions via quantum state change and measurements of the Pauli-Z. The resulting quantum features are then fed into a classical decoder, which is able to classify traffic in multiple classes such as browsing, streaming, VoIP and file transfer applications across them. The proposed hybrid architecture highlights the potential of intelligent traffic analysis for a quantum-enhanced learning system; it also lays the groundwork for future quantum-assisted cybersecurity solutions.

DOI
10.1109/iccvbic71195.2026.11689364

Related papers

Hybrid Quantum - Classical Neural Networks for Enhanced Network Anomaly Detection

Bokka Ramya Satya Priya, Odugu Srinivasa Rao

There is a pressing need for anomaly detection algorithms that can handle large amounts of diverse traffic data due to the quick growth of networked systems and the sophistication of contemporary cyberattacks. Despite the widespread use of conventional machine learning techniques for network intrusion detection, feature representation constraints, dataset imbalance, and the computational expense of scaling to vast problem spaces sometimes restrict their efficacy. In the meantime, new developments in quantum-assisted computation have opened up exciting possibilities for using quantum state changes to improve the feature learning process. Using the NF-UNSWNB15-v2 benchmark, this research presents HybridQCNN, a unique quantum-classical computing framework for binary classification of network traffic.The proposed architecture combines standard preprocessing techniques with an 8-qubit Parameterized Quantum Circuit (PQC) featuring multiple variational layers, where IsingXX and IsingYY entangling operations are applied to encode interfeature correlations, and a subsequent fully connected classical layer handles the final binary decision. A rigorous leakage-free data partitioning protocol was enforced, ensuring that all preprocessing transformations—including feature encoding, normalization, and threshold computation—were derived exclusively from the training subset, thereby preventing any information leakage from held-out partitions during evaluation. Experimental validation on a class-balanced subset of 60,000 traffic records yielded a classification accuracy of 97.33%, an F1-score of 0.9730, and a malicious traffic detection precision of 98.38%. Furthermore, the model achieved an AUC-ROC of 0.9861, reflecting strong class-level discriminability. Despite this performance, the entire model contains only 489 trainable parameters, underscoring the parameter efficiency of hybrid architectures relative to conventional deep learning baselines. These results suggest that integrating variational quantum circuits with classical inference modules provides an effective and scalable solution for network anomaly detection.

•Jan 1, 2026•0 citations

Quantum AI for Cybersecurity: A hybrid Quantum-Classical models for attack path analysis

Jessica A. Sciammarelli, Waqas Ahmed

Modern cyberattacks are increasingly complex, posing significant challenges to classical machine learning methods, particularly when labeled data is limited and feature interactions are highly non-linear. In this study we investigates the potential of hybrid quantum-classical learning to enhance feature representations for intrusion detection and explore possible quantum advantages in cybersecurity analytics. Using the UNSW-NB15 dataset, network traffic is transformed into structured feature vectors through classical preprocessing and normalization. Classical models, including Logistic Regression and Support Vector Machines with linear and RBF kernels, are evaluated on the full dataset to establish baseline performance under large-sample conditions. Simultaneously, a quantum-enhanced pipeline maps classical features into variational quantum circuits via angle encoding and entangling layers, executed on a CPU-based quantum simulator, with resulting quantum embeddings classified using a classical SVM. Experiments show that while classical models achieve higher overall accuracy with large datasets, quantum-enhanced representations demonstrate superior attack recall and improved class separability when data is scarce, suggesting that quantum feature spaces capture complex correlations inaccessible to shallow classical models. These results highlight the potential of quantum embeddings to improve generalization and representation quality in cybersecurity tasks and provide a reproducible framework for evaluating quantum advantages as quantum hardware and simulators continue to advance.

cs.CRCross-listedarXiv:2601.02237•Jan 6, 2026•0 citations

Encrypted network traffic analysis using quantum machine learning

Gokul Sunil Sodar, Akshay Murthy, Annapurna Jonnalagadda +1 more

There is an exponential growth in the encrypted network traffic due to the increased privacy concerns and secure communication needs. This growth has made traditional content- based based traffic analysis techniques ineffective to determine whether traffic is benign or malicious. As a result, security researchers have adopted the practice of examining HTTP header files to analyze encrypted network traffic. This involves inspecting IP addresses, packet sizes, and other metadata. However, these conventional methods face significant limitations in capturing complex temporal dependencies, adapting to evolving threats, and performing, under data sparsity or noise especially in the context of encrypted traffic where visibility is inherently restricted. Traditionally, machine learning and deep learning methods have been successfully used to classify packets as normal or an attack. With the ability to handle high-dimensional and complex nature of this metadata, Quantum Machine Learning (QML) offers a novel paradigm to potentially uncover more intricate patterns that are intractable for classical models. In this paper, we examine the usage of two quantum machine learning models: Quantum Support Vector Machine (QSVM) and Quantum K-Nearest Neighbors (QKNN). We have proposed hybrid quantum machine learning methods, wherein the data is encoded using quantum encodings and then classified using canonical machine learning models. We experimented with different quantum encodings such as angle and amplitude encoding. Our study was conducted on encrypted traffic classification datasets provided by the Canadian Institute of Cybersecurity. Our findings show that the proposed quantum and hybrid quantum models achieve performance comparable to the canonical machine learning models. Notably, the hybrid KNN and SVM models, when paired with amplitude encoding, demonstrated performance on par with or superior to their purely canonical counterparts. We hope that these results would be of interest not only just the researchers and academicians and also practitioners in Cybersecurity industry.

EPJ Quantum Technology•Jan 20, 2026•4 citations

Hybrid Quantum AI and Classical Machine Learning Model for Telecommunication Network Traffic Analysis

Syed Faraz Ahmed Naqvi, Mohammed Imroz Malik, Ashok Kumar Mishra +3 more

The paper presents a novel Hybrid Quantum AI and Classical Machine Learning (CML) Model for Telecommunication Network Traffic Analysis, integrating quantum computing's computational advantages with classical machine learning's stability. The methodology employs Quantum Feature Embedding (QFE) using Amplitude Encoding (AE) and Angle Encoding (AnE) to transform classical data into quantum states, improving pattern recognition. Feature Engineering (FE) is performed using Pandas for data preprocessing, ensuring optimal input for hybrid processing. The hybrid model leverages Quantum Neural Networks (QNNs) and Quantum Kernel Methods (QKM) for high-dimensional feature extraction, while Convolutional Neural Networks (CNNs) and Random Forests (RF) enhance interpretability and stability. Performance benchmarking based on Accuracy (ACC), Execution Time (ET), and Computational Complexity (CC) demonstrates that the proposed model outperforms classical approaches in speed and efficiency. Simulations using IBM Qiskit and TensorFlow Quantum (TFQ) validate the effectiveness of this framework. The proposed approach provides a scalable and optimized solution for real-time telecommunication network traffic management, suggesting the technique for future development in quantum-enhanced AI applications.

International Conference on Engineering Innovations and Technologies (ICoEIT)•Jul 4, 2025•2 citations

Quantum Anomaly Detection in network traffic using Variational Quantum Classifiers

Mir H M Ilham, Hardique Dasore, Abdulrahman Ababneh +5 more

The increasingly complex cybersecurity landscape requires more advanced network anomaly detection systems. Although, classical machine learning models are known to be effective, they reach computational bottlenecks when processing high-dimensional data. This study investigates the potential of Quantum Machine Learning (QML) for network traffic anomaly detection by evaluating four distinct Variational Quantum Classifier (VQC) architectures. A synthetic network traffic dataset is generated for the evaluations. The VQC models systematically varied feature encoding methods, parameterized ansatz circuits, quantum neural network types, and classical optimizers. Experimental results show that a trade-off exists between circuit expressivity and optimization stability. Deeper circuits (VQC-4) achieved higher accuracy of upto 89.0\%, while simultaneously being sensitive to training conditions. A shallower variant (VQC-1) under performed, although it had consistent and stable optimization curves. Class-dependent biases were also observed such as in VQC-2, where the model struggled to find an effective decision boundary, and produced a large number of false negatives. The best performing model in this study (VQC-3) combined ZFeatureMap with RealAmplitudes ansatz, optimized using ADAM. Comparative analysis against classical machine learning models such as Support Vector Machine and Random Forest reveal a performance gap, where classical models are able to achieve perfect classification performance on the synthetic data. It is concluded that classical algorithms remain dominant in their ability to classify structured data with relatively simple class separations. However, due to the observed potential of certain VQC configurations to learn decision boundaries to classify data, their utility for future applications in noisier, higher-dimensional problems is highlighted.

quant-pharXiv:2610.34635•Oct 27, 2026•0 citations

Quantum-Enhanced Network Intrusion Detection Using Variational Quantum Machine Learning

Keerthna. M. P, C. M. Nalayini, Jenifer Shylaja. M +1 more

Intrusion detection is an essential aspect of cybersecurity in fast-changing networked systems, but traditional machine learning-based IDS cannot scale or use high-dimensional traffic data easily. In this paper, a hybrid quantumclassical intrusion detection system (HQ-IDS) has been introduced, and it uses variational quantum circuits to enhance the learning and classification. Classical preprocessing techniques such as standardization and principal component analysis (PCA) are used to down sample and reduce features, which are then angle-encoded into quantum states and processed through parameterized quantum circuits with entangling layers. Binary classification is performed using quantum measurements combined with a classical readout layer, and the model is trained end-to-end via gradient-based optimization. Experimental results on synthetic intrusion data show that the proposed HQ-IDS achieves competitive accuracy while remaining scalable to noisy intermediate-scale quantum (NISQ) devices, emphasizing the possibility of hybrid quantum machine learning for future network security applications.

International Conference on Trends in Quantum Computing and Emerging Business Technologies (TQCEBT)•Apr 1, 2026•0 citations
As cyberattacks evolve in greater impact and complexity, they have Network traffic classification is a key component of any modern or intelligent cybersecurity system, which includes monitoring, managing network resources, detecting intrusions, and managing application-aware network operations. Unfortunately, with the complexity of networks increasing and ubiquitous use of encryption communication protocols, traditional traffic analysis methods were significantly diminished. To meet the challenges, a hybrid quantum-classical machine learning approach to the network traffic classification is proposed in this paper. The approach that is proposed in this paper utilizes the Dataset-Unicauca-Version2-87Atts, which originally contains approximately 3.57 million flow records. The experimental evaluation is performed on a balanced subset obtained after preprocessing and class balancing. To enhance the data quality and the capability to learn, a comprehensive preprocessing pipeline is employed, which contains feature selection, missing value handling, logarithmic data transformation, label encoding, and feature standardization. The whole effort combines a classical neural component with an angle embedding quantum circuit using strongly entangling quantum layers, all of which are assembled with PennyLane. The quantum layer processes four qubits and encodes network traffic patterns into multiple dimensions via quantum state change and measurements of the Pauli-Z. The resulting quantum features are then fed into a classical decoder, which is able to classify traffic in multiple classes such as browsing, streaming, VoIP and file transfer applications across them. The proposed hybrid architecture highlights the potential of intelligent traffic analysis for a quantum-enhanced learning system; it also lays the groundwork for future quantum-assisted cybersecurity solutions.
There is a pressing need for anomaly detection algorithms that can handle large amounts of diverse traffic data due to the quick growth of networked systems and the sophistication of contemporary cyberattacks. Despite the widespread use of conventional machine learning techniques for network intrusion detection, feature representation constraints, dataset imbalance, and the computational expense of scaling to vast problem spaces sometimes restrict their efficacy. In the meantime, new developments in quantum-assisted computation have opened up exciting possibilities for using quantum state changes to improve the feature learning process. Using the NF-UNSWNB15-v2 benchmark, this research presents HybridQCNN, a unique quantum-classical computing framework for binary classification of network traffic.The proposed architecture combines standard preprocessing techniques with an 8-qubit Parameterized Quantum Circuit (PQC) featuring multiple variational layers, where IsingXX and IsingYY entangling operations are applied to encode interfeature correlations, and a subsequent fully connected classical layer handles the final binary decision. A rigorous leakage-free data partitioning protocol was enforced, ensuring that all preprocessing transformations—including feature encoding, normalization, and threshold computation—were derived exclusively from the training subset, thereby preventing any information leakage from held-out partitions during evaluation. Experimental validation on a class-balanced subset of 60,000 traffic records yielded a classification accuracy of 97.33%, an F1-score of 0.9730, and a malicious traffic detection precision of 98.38%. Furthermore, the model achieved an AUC-ROC of 0.9861, reflecting strong class-level discriminability. Despite this performance, the entire model contains only 489 trainable parameters, underscoring the parameter efficiency of hybrid architectures relative to conventional deep learning baselines. These results suggest that integrating variational quantum circuits with classical inference modules provides an effective and scalable solution for network anomaly detection.
Modern cyberattacks are increasingly complex, posing significant challenges to classical machine learning methods, particularly when labeled data is limited and feature interactions are highly non-linear. In this study we investigates the potential of hybrid quantum-classical learning to enhance feature representations for intrusion detection and explore possible quantum advantages in cybersecurity analytics. Using the UNSW-NB15 dataset, network traffic is transformed into structured feature vectors through classical preprocessing and normalization. Classical models, including Logistic Regression and Support Vector Machines with linear and RBF kernels, are evaluated on the full dataset to establish baseline performance under large-sample conditions. Simultaneously, a quantum-enhanced pipeline maps classical features into variational quantum circuits via angle encoding and entangling layers, executed on a CPU-based quantum simulator, with resulting quantum embeddings classified using a classical SVM. Experiments show that while classical models achieve higher overall accuracy with large datasets, quantum-enhanced representations demonstrate superior attack recall and improved class separability when data is scarce, suggesting that quantum feature spaces capture complex correlations inaccessible to shallow classical models. These results highlight the potential of quantum embeddings to improve generalization and representation quality in cybersecurity tasks and provide a reproducible framework for evaluating quantum advantages as quantum hardware and simulators continue to advance.
There is an exponential growth in the encrypted network traffic due to the increased privacy concerns and secure communication needs. This growth has made traditional content- based based traffic analysis techniques ineffective to determine whether traffic is benign or malicious. As a result, security researchers have adopted the practice of examining HTTP header files to analyze encrypted network traffic. This involves inspecting IP addresses, packet sizes, and other metadata. However, these conventional methods face significant limitations in capturing complex temporal dependencies, adapting to evolving threats, and performing, under data sparsity or noise especially in the context of encrypted traffic where visibility is inherently restricted. Traditionally, machine learning and deep learning methods have been successfully used to classify packets as normal or an attack. With the ability to handle high-dimensional and complex nature of this metadata, Quantum Machine Learning (QML) offers a novel paradigm to potentially uncover more intricate patterns that are intractable for classical models. In this paper, we examine the usage of two quantum machine learning models: Quantum Support Vector Machine (QSVM) and Quantum K-Nearest Neighbors (QKNN). We have proposed hybrid quantum machine learning methods, wherein the data is encoded using quantum encodings and then classified using canonical machine learning models. We experimented with different quantum encodings such as angle and amplitude encoding. Our study was conducted on encrypted traffic classification datasets provided by the Canadian Institute of Cybersecurity. Our findings show that the proposed quantum and hybrid quantum models achieve performance comparable to the canonical machine learning models. Notably, the hybrid KNN and SVM models, when paired with amplitude encoding, demonstrated performance on par with or superior to their purely canonical counterparts. We hope that these results would be of interest not only just the researchers and academicians and also practitioners in Cybersecurity industry.
The paper presents a novel Hybrid Quantum AI and Classical Machine Learning (CML) Model for Telecommunication Network Traffic Analysis, integrating quantum computing's computational advantages with classical machine learning's stability. The methodology employs Quantum Feature Embedding (QFE) using Amplitude Encoding (AE) and Angle Encoding (AnE) to transform classical data into quantum states, improving pattern recognition. Feature Engineering (FE) is performed using Pandas for data preprocessing, ensuring optimal input for hybrid processing. The hybrid model leverages Quantum Neural Networks (QNNs) and Quantum Kernel Methods (QKM) for high-dimensional feature extraction, while Convolutional Neural Networks (CNNs) and Random Forests (RF) enhance interpretability and stability. Performance benchmarking based on Accuracy (ACC), Execution Time (ET), and Computational Complexity (CC) demonstrates that the proposed model outperforms classical approaches in speed and efficiency. Simulations using IBM Qiskit and TensorFlow Quantum (TFQ) validate the effectiveness of this framework. The proposed approach provides a scalable and optimized solution for real-time telecommunication network traffic management, suggesting the technique for future development in quantum-enhanced AI applications.
The increasingly complex cybersecurity landscape requires more advanced network anomaly detection systems. Although, classical machine learning models are known to be effective, they reach computational bottlenecks when processing high-dimensional data. This study investigates the potential of Quantum Machine Learning (QML) for network traffic anomaly detection by evaluating four distinct Variational Quantum Classifier (VQC) architectures. A synthetic network traffic dataset is generated for the evaluations. The VQC models systematically varied feature encoding methods, parameterized ansatz circuits, quantum neural network types, and classical optimizers. Experimental results show that a trade-off exists between circuit expressivity and optimization stability. Deeper circuits (VQC-4) achieved higher accuracy of upto 89.0\%, while simultaneously being sensitive to training conditions. A shallower variant (VQC-1) under performed, although it had consistent and stable optimization curves. Class-dependent biases were also observed such as in VQC-2, where the model struggled to find an effective decision boundary, and produced a large number of false negatives. The best performing model in this study (VQC-3) combined ZFeatureMap with RealAmplitudes ansatz, optimized using ADAM. Comparative analysis against classical machine learning models such as Support Vector Machine and Random Forest reveal a performance gap, where classical models are able to achieve perfect classification performance on the synthetic data. It is concluded that classical algorithms remain dominant in their ability to classify structured data with relatively simple class separations. However, due to the observed potential of certain VQC configurations to learn decision boundaries to classify data, their utility for future applications in noisier, higher-dimensional problems is highlighted.
Intrusion detection is an essential aspect of cybersecurity in fast-changing networked systems, but traditional machine learning-based IDS cannot scale or use high-dimensional traffic data easily. In this paper, a hybrid quantumclassical intrusion detection system (HQ-IDS) has been introduced, and it uses variational quantum circuits to enhance the learning and classification. Classical preprocessing techniques such as standardization and principal component analysis (PCA) are used to down sample and reduce features, which are then angle-encoded into quantum states and processed through parameterized quantum circuits with entangling layers. Binary classification is performed using quantum measurements combined with a classical readout layer, and the model is trained end-to-end via gradient-based optimization. Experimental results on synthetic intrusion data show that the proposed HQ-IDS achieves competitive accuracy while remaining scalable to noisy intermediate-scale quantum (NISQ) devices, emphasizing the possibility of hybrid quantum machine learning for future network security applications.