Modeling Wavelet Transformed Quantum Support Vector for Network Intrusion Detection

2025-12-01

AI Summary

Anomaly detection in IoT network traffic remains challenging due to high dimensionality, temporal dynamics, and noise sensitivity. Method: This paper proposes a hybrid quantum-classical framework integrating quantum Haar wavelet packet transform (QHWPT) with quantum support vector machine (QSVM). Traffic data are encoded via amplitude encoding; multi-level QHWPT extracts time-frequency features, followed by Shannon entropy and chi-square test for feature selection. A fidelity-based quantum kernel is designed and optimized using the simultaneous perturbation stochastic approximation (SPSA) algorithm for robust kernel learning. Contribution/Results: Evaluated on BoT-IoT and IoT-23 datasets, the method achieves 96.67% and 89.67% classification accuracy under noise-free and depolarizing noise conditions, respectively—outperforming state-of-the-art quantum autoencoder approaches by over 7 percentage points. It demonstrates significantly enhanced resilience to quantum noise and improved intrusion detection capability in realistic IoT environments.

Technology Category

• Machine Learning: Quantum Machine Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Application Domains: Internet of Things, Sensor Networks & Smart Cities

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Network traffic anomaly detection is a critical cy- bersecurity 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 quan- tum 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 train- ing 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.

Problem

• Detects network traffic anomalies in IoT environments using quantum-classical methods.
• Integrates Quantum Support Vector Machine with wavelet transforms for improved classification.
• Optimizes quantum kernels under noise to achieve high detection accuracy.

Innovation

• Quantum Haar Wavelet Packet Transform for feature extraction
• Amplitude-encoded quantum state preparation and fidelity-based kernels
• Hybrid training with SPSA optimizer for quantum kernel optimization