Abstract:
Modern communication environments ranging from smart mobility infrastructures to digitally integrated healthcare systems demand adaptable and trustworthy network security. In this situation, Software-Defined Networks (SDNs) play a vital role by providing programmable control and global visibility, enabling rapid policy updates and fine-grained traffic management. As a result, the need for efficient and interpretable intrusion detection becomes increasingly critical. To achieve this, SDN controllers require real-time intrusion detection systems (IDS) models capable of adapting to evolving traffic behaviors while operating within strict latency and resource constraints. However, most existing deep learning and ensemble-based models either rely on heavy architectures or non-transparent optimization processes that increase inference delay, limiting their deployability in latency-sensitive SDN controllers. This paper presents Quantum Amplitude Tabular Network (QATNet), a hybrid quantum-classical framework that integrates amplitude encoding, a shallow Variational Quantum Circuit (VQC), and an attentive TabNet head for flow-based intrusion detection. Unlike conventional deep or ensemble methods, QATNet leverages quantum-inspired feature transformations to reshape the geometric structure of network flows, enhancing class separability while maintaining controller-side efficiency. Experiments on two modern benchmarks OD-IDS2022 and CIC-IDS2018 demonstrate that QATNet consistently outperforms classical PCA-TabNet and amplitude-only baselines in accuracy, macro-F1, and Area Under the Receiver Operating Characteristic curve (AUROC), achieving consistent accuracy and F1-score performance across different qubit budgets (Q≤6). Noise-simulation studies using IBM’s FakeNairobi and FakeJakarta backend confirm robustness under realistic quantum noise, while runtime analysis verifies that inference latency (0.012 ms/sample) satisfies SDN controller timing requirements. The results prove that lightweight hybrid encoders provide resource-aware and noise-tolerant intrusion detection advancing the practical integration of quantum-enhanced learning in next-generation SDN security analytics.