Q-DEFENDER PRO: A HYBRID CLASSICAL QUANTUM-ASSISTED NETWORK INTRUSION DETECTION SYSTEM

To address the rising volume of network-based threats (e.g.DDoS, port scans, brute-force attacks, and malware) you need advanced intrusion detection systems.Even though recent advancements in quantum machine learning approaches like QNNs on noisy hardware exhibit strong performance at binary detection methods, they do not have classical integration, interpretability, or practical deployment tools.The current project proposes Q-Defender Pro as a hybrid classical and quantum-assisted network intrusion detection system that combines an RF classifier with a simulated VQC in a weighted ensemble of 60% classical.The AS system will have SHAP based explainability based on feature importance and interaction, a full GUI for end-toend workflow (dataset loading and generation, pre-processing, training, ensemble evaluation, online prediction, and export of data), and support for multi-class detection.Due to its hybrid design and user-friendly interface, the proposed solution will offer better usability, interpretability, and accessibility than pure quantum solutions.