<ul><li>Quantum computing is explored for enhancing network anomaly detection through a quantum generative adversarial network (QGAN) architecture.</li><li>The QGAN leverages variational quantum circuits (VQCs) with techniques like time-window shifting, data re-uploading, and successive data injection (SuDaI).</li><li>The method efficiently encodes multivariate time series data into quantum states to address hardware limitations, achieving high accuracy, recall, and F1-scores in anomaly detection.</li><li>The QGAN, trained using the parameter shift rule, outperformed a classical GAN with competitive results using a compact architecture of only 80 parameters, showing effectiveness even under noisy conditions.</li></ul>

Enhancing Network Anomaly Detection with Quantum GANs and Successive Data Injection for Multivariate Time Series

Discover more