{"id":6438,"date":"2025-10-20T22:15:15","date_gmt":"2025-10-21T02:15:15","guid":{"rendered":"https:\/\/lincslab.ca\/?p=6438"},"modified":"2026-04-24T14:43:08","modified_gmt":"2026-04-24T18:43:08","slug":"quantum-gans-for-smarter-network-anomaly-detection","status":"publish","type":"post","link":"https:\/\/lincslab.ca\/en\/quantum-gans-for-smarter-network-anomaly-detection\/","title":{"rendered":"Quantum GANs for Smarter Network Anomaly Detection"},"content":{"rendered":"\t\t
\n\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Quantum GANs for Smarter Network Anomaly Detection<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\n\t\t\t\t\t\t<\/span>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

As modern communication networks grow in complexity, traditional anomaly detection techniques face challenges in identifying sophisticated threats such as distributed denial-of-service (DDoS) or stealth attacks. In our latest study, we explore how quantum machine learning<\/strong> can offer a new frontier for cybersecurity analytics.<\/p>

In our recent paper, “Enhancing Network Anomaly Detection with Quantum GANs and Successive Data Injection for Multivariate Time Series<\/span><\/a>” [arXiv<\/a>], Hammami, Cherkaoui, and Wang<\/strong> present a Quantum Generative Adversarial Network (QGAN)<\/strong> designed for detecting anomalies in multivariate network time-series data<\/strong>. The model integrates variational quantum circuits<\/strong>, data re-uploading<\/strong>, and a novel Successive Data Injection (SuDaI)<\/strong> technique that efficiently maps high-dimensional classical data into quantum states\u2014overcoming current hardware limits such as the small number of available qubits.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Figure 1 \u2014 Quantum Discriminator Circuit.<\/strong>
The discriminator circuit used in the proposed Quantum GAN architecture for network anomaly detection. It evaluates generated samples against real multivariate time-series data to guide the generator toward realistic outputs.<\/i><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Trained on the CIC-CIDDS-2018<\/strong> dataset, the proposed model achieves 99% accuracy<\/strong> and an F1-score of 0.98<\/strong>, matching the performance of deep learning models that use thousands of parameters while requiring only 80 trainable parameters<\/strong>. Even under simulated quantum noise, the QGAN maintained robust performance, highlighting its potential for real-world deployment on near-term quantum devices.<\/p>

This research demonstrates that quantum-enhanced learning can deliver compact, efficient, and resilient models for network security in 6G and beyond<\/strong>, opening the door to hybrid quantum\u2013classical cybersecurity systems.<\/p>

Authors: Wajdi Hammami, Soumaya Cherkaoui, and Shengrui Wang (Polytechnique Montr\u00e9al, Universit\u00e9 de Sherbrooke).<\/em><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\n