Quantum Enhanced Anomaly Detection for ADS-B Data using Hybrid Deep Learning

2025-09-19

AI Summary

To address the low computational efficiency in high-dimensional feature processing and poor model interpretability in ADS-B anomaly detection, this paper proposes a Hybrid Fully Connected Quantum Neural Network (H-FQNN), integrating quantum superposition and entanglement into a classical deep learning architecture to construct an end-to-end quantum-enhanced detection framework. Methodologically, we design a co-training mechanism between quantum parameterized layers and classical feedforward structures, systematically evaluate multiple loss functions, and conduct empirical validation on a public ADS-B dataset. Experimental results demonstrate that H-FQNN achieves an accuracy of 90.17%–94.05% while maintaining computational feasibility—matching the performance of the best classical fully connected network. This work presents the first empirical validation of quantum neural networks’ effective adaptation and practical competitiveness in aviation surveillance anomaly detection, establishing a reproducible technical paradigm for quantum machine learning in safety-critical air traffic management applications.

Technology Category

• Machine Learning: Quantum Machine Learning
• Computer Vision: Adversarial Attacks & Robustness
• Multiagent Systems: Adversarial Agents

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The emerging field of Quantum Machine Learning (QML) has shown promising advantages in accelerating processing speed and effectively handling the high dimensionality associated with complex datasets. Quantum Computing (QC) enables more efficient data manipulation through the quantum properties of superposition and entanglement. In this paper, we present a novel approach combining quantum and classical machine learning techniques to explore the impact of quantum properties for anomaly detection in Automatic Dependent Surveillance-Broadcast (ADS-B) data. We compare the performance of a Hybrid-Fully Connected Quantum Neural Network (H-FQNN) with different loss functions and use a publicly available ADS-B dataset to evaluate the performance. The results demonstrate competitive performance in detecting anomalies, with accuracies ranging from 90.17% to 94.05%, comparable to the performance of a traditional Fully Connected Neural Network (FNN) model, which achieved accuracies between 91.50% and 93.37%.

Problem

• Detecting anomalies in ADS-B data
• Combining quantum and classical machine learning
• Evaluating hybrid quantum neural network performance

Innovation

• Hybrid quantum-classical deep learning
• Quantum neural network for anomaly detection
• Superposition and entanglement properties utilization