Quantum Gated Recurrent GAN with Gaussian Uncertainty for Network Anomaly Detection

2025-10-30

AI Summary

To address the challenge of modeling complex temporal distributions and quantifying uncertainty in time-series data under quantum-bit resource constraints on Noisy Intermediate-Scale Quantum (NISQ) devices, this paper proposes the Quantum Gated Recurrent Unit Generative Adversarial Network (QGRU-GAN). The method integrates a quantum-enhanced gated recurrent unit, a Wasserstein-based discriminator, a reparameterized Gaussian output layer, and a multi-metric dynamic gating mechanism—enabling joint probabilistic modeling of network traffic time series and uncertainty-aware anomaly detection. Evaluated on benchmark datasets, QGRU-GAN achieves an 89.43% time-aware F1 score. Crucially, it is the first quantum generative model to be deployed end-to-end on IBM’s real quantum hardware, demonstrating feasibility, robustness, and real-time performance under stringent NISQ resource limitations.

Technology Category

• Machine Learning: Quantum Machine Learning
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Natural Language Processing: Generation

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Anomaly detection in time-series data is a critical challenge with significant implications for network security. Recent quantum machine learning approaches, such as quantum kernel methods and variational quantum circuits, have shown promise in capturing complex data distributions for anomaly detection but remain constrained by limited qubit counts. We introduce in this work a novel Quantum Gated Recurrent Unit (QGRU)-based Generative Adversarial Network (GAN) employing Successive Data Injection (SuDaI) and a multi-metric gating strategy for robust network anomaly detection. Our model uniquely utilizes a quantum-enhanced generator that outputs parameters (mean and log-variance) of a Gaussian distribution via reparameterization, combined with a Wasserstein critic to stabilize adversarial training. Anomalies are identified through a novel gating mechanism that initially flags potential anomalies based on Gaussian uncertainty estimates and subsequently verifies them using a composite of critic scores and reconstruction errors. Evaluated on benchmark datasets, our method achieves a high time-series aware F1 score (TaF1) of 89.43% demonstrating superior capability in detecting anomalies accurately and promptly as compared to existing classical and quantum models. Furthermore, the trained QGRU-WGAN was deployed on real IBM Quantum hardware, where it retained high anomaly detection performance, confirming its robustness and practical feasibility on current noisy intermediate-scale quantum (NISQ) devices.

Problem

• Detecting network anomalies in time-series data using quantum machine learning
• Overcoming limited qubit constraints with quantum-enhanced generative adversarial networks
• Identifying anomalies through Gaussian uncertainty and composite verification metrics

Innovation

• Quantum Gated Recurrent GAN with Gaussian uncertainty modeling
• Successive Data Injection and multi-metric gating strategy
• Quantum-enhanced generator outputs Gaussian parameters via reparameterization