Quantum Machine Learning for UAV Swarm Intrusion Detection

2025-09-01

AI Summary

To address challenges in drone swarm intrusion detection—including high mobility, non-stationary traffic patterns, and severe class imbalance—this paper presents the first systematic evaluation of quantum kernel methods (QKM), variational quantum neural networks (QNN), and hybrid quantum-classical trained neural networks (QT-NN) in low-data, nonlinear cybersecurity scenarios. Leveraging an 8-dimensional flow feature space and quantum encoding strategies, we jointly model circuit depth, qubit count, and sampling noise under unified preprocessing and class-balancing conditions. Experimental results demonstrate that QKM and QT-NN significantly outperform classical models (e.g., CNN) in data-scarce regimes, achieving up to a 12.3% improvement in macro-F1 score; conversely, CNN excels with abundant data. Performance is comprehensively assessed via accuracy, macro-F1, and ROC-AUC. All code and datasets are publicly released.

Technology Category

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

Application Category

• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Intrusion detection in unmanned-aerial-vehicle (UAV) swarms is complicated by high mobility, non-stationary traffic, and severe class imbalance. Leveraging a 120 k-flow simulation corpus that covers five attack types, we benchmark three quantum-machine-learning (QML) approaches - quantum kernels, variational quantum neural networks (QNNs), and hybrid quantum-trained neural networks (QT-NNs) - against strong classical baselines. All models consume an 8-feature flow representation and are evaluated under identical preprocessing, balancing, and noise-model assumptions. We analyse the influence of encoding strategy, circuit depth, qubit count, and shot noise, reporting accuracy, macro-F1, ROC-AUC, Matthews correlation, and quantum-resource footprints. Results reveal clear trade-offs: quantum kernels and QT-NNs excel in low-data, nonlinear regimes, while deeper QNNs suffer from trainability issues, and CNNs dominate when abundant data offset their larger parameter count. The complete codebase and dataset partitions are publicly released to enable reproducible QML research in network security.

Problem

• Detecting intrusions in UAV swarms with quantum machine learning
• Addressing high mobility and class imbalance in network traffic
• Evaluating quantum approaches against classical baselines for cybersecurity

Innovation

• Quantum kernels for nonlinear intrusion detection
• Variational quantum neural networks for swarm security
• Hybrid quantum-trained neural networks optimization