A hybrid SHA-256 and variational quantum classifier framework for simulation-based intrusion detection in SDN-IoT networks
Discover Internet of Things · 15.08.2026 · 6 (1)
DOI: 10.1007/s43926-026-00474-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift Discover Internet of Things, online erschienen am 15.08.2026. Verfasst von Pooja Agarwal und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The convergence of Software-Defined Networking (SDN) with Internet of Things (IoT) introduces critical security vulnerabilities requiring adaptive detection mechanisms. This paper presents QEIDS, a quantum-enhanced intrusion detection system combining SHA-256 cryptographic fingerprinting with variational quantum classification (VQC) for efficient threat detection in SDN-IoT networks. The three-layer architecture employs SHA-256 hash matching for deterministic primary filtering (handling 60–70% of traffic at 4,000 packets/s), a Variational Quantum Classifier using EfficientSU2 ansatz with ZFeatureMap encoding on 9 qubits for adaptive threat classification of ambiguous traffic, and a decision-tree fallback for interpretable edge-case handling. We establish polynomial sample complexity bounds of O(n³ log n) for the VQC-based learning framework with strategic initialization, compared to higher polynomial or exponential worst-case bounds for partition function computation in classical energy-based models. Extensive evaluation across four benchmark datasets NSL-KDD (148,517 samples, network intrusions), PhiUSIIL (235,162 samples, phishing URLs), Android Permissions (29,932 samples, malware), and Email Spam (5,572 samples) demonstrates 97.34% mean detection accuracy with 35% reduction in computational footprint compared to classical deep learning baselines. The hybrid framework achieves 96.8 ms average detection latency under MATLAB 2024b classical simulation, suggesting potential compliance with the sub-100 ms SDN flow-processing threshold; however, hardware validation on actual NISQ devices remains as future work. Additionally, QEIDS attains 99.2% recall on critical attack types (DDoS, probe, and zero-day exploits), 84.27% average zero-shot accuracy on previously unseen attack patterns, and 4.51× faster training convergence compared to CNN-GRU baselines. All results are simulation-based and represent proof-of-concept validation; practical quantum advantage claims require future verification on real quantum hardware.
Zitieren
APA
Agarwal, P., Srivastava, R. K., Nishad, D. K., Mossie, M. A., & Gupta, S. (2026). A hybrid SHA-256 and variational quantum classifier framework for simulation-based intrusion detection in SDN-IoT networks. Discover Internet of Things, 6(1). https://doi.org/10.1007/s43926-026-00474-9
Vancouver
Agarwal P, Srivastava RK, Nishad DK, Mossie MA, Gupta S. A hybrid SHA-256 and variational quantum classifier framework for simulation-based intrusion detection in SDN-IoT networks. Discover Internet of Things. 2026;6(1). doi:10.1007/s43926-026-00474-9
BibTeX
@article{Agarwal2026,
author = {Agarwal, Pooja and Srivastava, R. K. and Nishad, D. K. and Mossie, Molla Addisu and Gupta, Sandeep},
title = {A hybrid SHA-256 and variational quantum classifier framework for simulation-based intrusion detection in SDN-IoT networks},
journal = {Discover Internet of Things},
year = {2026},
volume = {6},
number = {1},
doi = {10.1007/s43926-026-00474-9}
}
EUVIMED