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

Quantum versus Classical Support Vector Machines for Anomaly Detection in the Internet of Things: An Empirical Comparison

Ismael Foko Tekoujou, Tifu Kelison Tifu

Published Jan 1, 2026• 0 citations
Publisher
DOI
10.2139/ssrn.7350261

Related papers

Anomaly Detection Based on Quantum Support Vector Machines: A Comparative Study with Classical SVM

Abdallah Ahmed Wajdi, Houneida Sakly, Naoufel Kraïem

Lecture notes in computer science•Jan 1, 2026•0 citations

Quantum Anomaly Detection for Advanced Persistent Threats Using Quantum Support Vector Machines

Jaideep Rukmangadan, Seema Vasudevan

International Conference on Research and Development in Information, Communication, and Computing Technologies•Jan 1, 2025•0 citations

Quantum-enhanced Versus Classical Support Vector Machine: An Application to Stock Index Forecasting

Mathieu Mercadier

•Jan 1, 2023•2 citations

Quantum-Enhanced Versus Classical Support Vector Machine: An Application to Stock Index Forecasting

Mathieu Mercadier

•Jan 1, 2024•0 citations

A Hybrid Post Quantum Cryptography and Quantum Machine Learning Framework for Secure IoT Anomaly Detection

Lokesh B S, Narasimha Kaulgud

Abstract The rapid expansion of Internet of Things (IoT) infrastructures has heightened their exposure to sophisticated adversaries, including those equipped with quantum capabilities. This work introduces a hybrid framework that integrates post-quantum cryptography (PQC), quantum key distribution (QKD), and quantum machine learning (QML) to deliver quantum-resilient anomaly detection. A novel PQC-IoT dataset is generated using real-time Raspberry Pi sensors, enriched with 30+ features spanning 12 traffic classes (9 attacks, 3 benign), and incorporating PQC-specific metadata such as encryption latency and ciphertext size. Security is enforced through Kyber-512 encryption and a BB84-based QKD channel, while anomaly detection is performed using a quantum support vector machine (qSVM). Experimental results show that qSVM consistently outperforms classical SVM and XGBoost by 4--7% in accuracy, precision, recall, and F1-score, achieving up to 97.6% accuracy with encryption overhead limited to 5--7%. The framework maintains a Quantum Bit Error Rate (QBER) below 11% under noise models, validating its robustness. To the best of our knowledge, this is the first reproducible benchmark that unifies PQC, QKD, and QML into a single pipeline, offering a practical pathway toward quantum-secure IoT anomaly detection.

•Sep 18, 2025•1 citation

Modeling Wavelet Transformed Quantum Support Vector for Network Intrusion Detection

Swati Kumari, Shiva Raj Pokhrel, Swathi Chandrasekhar +5 more

Network traffic anomaly detection is a critical cybersecurity challenge requiring robust solutions for complex Internet of Things (IoT) environments. We present a novel hybrid quantum-classical framework integrating an enhanced Quantum Support Vector Machine (QSVM) with the Quantum Haar Wavelet Packet Transform (QWPT) for superior anomaly classification under realistic noisy intermediate-scale Quantum conditions. Our methodology employs amplitude-encoded quantum state preparation, multi-level QWPT feature extraction, and behavioral analysis via Shannon Entropy profiling and Chi-square testing. Features are classified using QSVM with fidelity-based quantum kernels optimized through hybrid training with simultaneous perturbation stochastic approximation (SPSA) optimizer. Evaluation under noiseless and depolarizing noise conditions demonstrates exceptional performance: 96.67% accuracy on BoT-IoT and 89.67% on IoT-23 datasets, surpassing quantum autoencoder approaches by over 7 percentage points.

quant-pharXiv:2512.01365•Dec 2, 2025•6 citations
Abstract The rapid expansion of Internet of Things (IoT) infrastructures has heightened their exposure to sophisticated adversaries, including those equipped with quantum capabilities. This work introduces a hybrid framework that integrates post-quantum cryptography (PQC), quantum key distribution (QKD), and quantum machine learning (QML) to deliver quantum-resilient anomaly detection. A novel PQC-IoT dataset is generated using real-time Raspberry Pi sensors, enriched with 30+ features spanning 12 traffic classes (9 attacks, 3 benign), and incorporating PQC-specific metadata such as encryption latency and ciphertext size. Security is enforced through Kyber-512 encryption and a BB84-based QKD channel, while anomaly detection is performed using a quantum support vector machine (qSVM). Experimental results show that qSVM consistently outperforms classical SVM and XGBoost by 4--7% in accuracy, precision, recall, and F1-score, achieving up to 97.6% accuracy with encryption overhead limited to 5--7%. The framework maintains a Quantum Bit Error Rate (QBER) below 11% under noise models, validating its robustness. To the best of our knowledge, this is the first reproducible benchmark that unifies PQC, QKD, and QML into a single pipeline, offering a practical pathway toward quantum-secure IoT anomaly detection.
Network traffic anomaly detection is a critical cybersecurity challenge requiring robust solutions for complex Internet of Things (IoT) environments. We present a novel hybrid quantum-classical framework integrating an enhanced Quantum Support Vector Machine (QSVM) with the Quantum Haar Wavelet Packet Transform (QWPT) for superior anomaly classification under realistic noisy intermediate-scale Quantum conditions. Our methodology employs amplitude-encoded quantum state preparation, multi-level QWPT feature extraction, and behavioral analysis via Shannon Entropy profiling and Chi-square testing. Features are classified using QSVM with fidelity-based quantum kernels optimized through hybrid training with simultaneous perturbation stochastic approximation (SPSA) optimizer. Evaluation under noiseless and depolarizing noise conditions demonstrates exceptional performance: 96.67% accuracy on BoT-IoT and 89.67% on IoT-23 datasets, surpassing quantum autoencoder approaches by over 7 percentage points.