Modeling Quantum Autoencoder Trainable Kernel for IoT Anomaly Detection

2025-11-26

AI Summary

To address the limited robustness of conventional methods and the deployment challenges of deep learning models on Noisy Intermediate-Scale Quantum (NISQ) devices for high-dimensional IoT traffic anomaly detection, this paper proposes a quantum machine learning framework. It employs a Quantum Autoencoder (QAE) for efficient feature compression and a trainable-kernel Quantum Support Vector Classifier (QSVC) for anomaly identification. Crucially, we introduce moderate-strength depolarizing noise as an implicit regularizer, significantly enhancing model generalization and hardware robustness. Experiments are conducted on both IBM’s real quantum processors and ideal simulators across three public datasets. Results demonstrate superior accuracy over classical baselines while maintaining practical deployability on NISQ hardware. To our knowledge, this is the first work to empirically validate a practically useful quantum advantage for IoT security on actual quantum devices.

Technology Category

• Machine Learning: Quantum Machine Learning
• Computer Vision: Adversarial Attacks & Robustness
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Escalating cyber threats and the high-dimensional complexity of IoT traffic have outpaced classical anomaly detection methods. While deep learning offers improvements, computational bottlenecks limit real-time deployment at scale. We present a quantum autoencoder (QAE) framework that compresses network traffic into discriminative latent representations and employs quantum support vector classification (QSVC) for intrusion detection. Evaluated on three datasets, our approach achieves improved accuracy on ideal simulators and on the IBM Quantum hardware demonstrating practical quantum advantage on current NISQ devices. Crucially, moderate depolarizing noise acts as implicit regularization, stabilizing training and enhancing generalization. This work establishes quantum machine learning as a viable, hardware-ready solution for real-world cybersecurity challenges.

Problem

• Quantum autoencoder compresses IoT traffic for anomaly detection
• Quantum support vector classification improves intrusion detection accuracy
• Moderate noise stabilizes training and enhances generalization on NISQ devices

Innovation

• Quantum autoencoder compresses IoT traffic into latent representations
• Quantum support vector classification enables intrusion detection on NISQ devices
• Moderate depolarizing noise stabilizes training as implicit regularization