Asymmetric class-conditional routing in a federated quantum mixture-of-experts improves imbalanced intrusion detection in edge industrial IoT networks
4 affiliations
- 1Department of Cyber Security, Faculty of Science and Information Technology, Irbid National University
- 2Faculty of Computer and Information Technology, Sana’a University
- 3Department of Artificial Intelligence and Data Science, Faculty of Science and Information Technology, Irbid National University
- 4Department of Computer Science, Faculty of Information Technology, Ajloun National University
Abstract
Intrusion detection systems (IDS) deployed in Edge Industrial Internet of Things (Edge-IIoT) environments face three critical and interrelated challenges: (i) extreme class imbalance, where tail-class attack categories may be outnumbered by benign traffic at ratios exceeding 700:1; (ii) competitive expert collapse in gating mechanisms relying on softmax normalization, which prevents sparse, class-conditional routing; and (iii) statistical heterogeneity across geographically distributed edge nodes with non-IID local traffic distributions. Existing federated learning solutions address these challenges in isolation, yielding suboptimal tail-class detection. We propose FedQMoE-IDS, a novel federated quantum mixture-of-experts framework that jointly resolves all three challenges through three synergistic innovations: (1) a class-balanced asymmetric focal loss with per-class focusing parameters γ c that independently modulate head- and tail-class gradients via effective-number weighting; (2) a normalized sigmoid gating mechanism with auxiliary-loss-free dynamic bias load balancing, replacing softmax to achieve genuine sparse activation with exact zero weights and class-conditional expert routing; and (3) a selective federated aggregation strategy that partitions the parameter space into shared (FedDyn-aggregated CNN+KAN+classifier), locally retained (personalized gating networks), and periodically exchanged (variational quantum circuit experts) components. The three-stage MoE architecture cascades 1D-CNN feature extractors, variational quantum circuit (VQC) encoders operating in Hilbert space, and Kolmogorov–Arnold Network (KAN) spline experts, each governed by independent sigmoid top-K gates. We conduct experiments under a realistic non-IID federated setting with N=10 Edge-IIoT clients partitioned via a Dirichlet distribution ( α =0.3 ), and we compare against parameter-matched classical baselines (deeper CNN and softmax-gated MoE), personalized federated MoE (FedMoE, pFedMoE), and federated class-imbalance methods. Comprehensive experiments on UNSW-NB15, Edge-IIoTset, and CIC-IDS2017 with five-seed evaluation and Bonferroni-corrected Wilcoxon signed-rank tests demonstrate that FedQMoE-IDS achieves 99.20% accuracy and 98.40% macro F1-score on UNSW-NB15, and 99.80% accuracy on Edge-IIoTset—surpassing recent state-of-the-art methods including centralized deep learning, federated LSTM, and transformer-based IDS. All improvements are statistically significant ( p < 0.05 ). The full source code and configuration files are publicly available to enable independent reproduction.
Related
- Causality-driven hybrid intrusion detection with entropy-aware feature learning and federated intelligence
- IFC-HFlowVAE: A self-enhancing generative framework with structural anchoring for imbalanced clinical data augmentation
- An EfficientNet hybrid deep learning detection framework of network intrusion with an optimized mixture-of-experts architecture
- Attention-based intrusion detection using transformer networks on UNSW-NB15
- Parrot dandelion optimizer-based routing and spiking neural network enabled intrusion detection in underwater IoT
BibTeX
@article{abdelhaliem2026asymmetric,
title = {{Asymmetric class-conditional routing in a federated quantum mixture-of-experts improves imbalanced intrusion detection in edge industrial IoT networks}},
author = {Amr H. Abdelhaliem and Mohammed Tawfik and Nedal Al Tamimi and Islam S. Fathi},
journal = {Scientific Reports},
year = {2026},
month = sep,
doi = {10.1038/s41598-026-71421-5},
url = {https://doi.org/10.1038/s41598-026-71421-5},
note = {CC BY},
}
RIS
TY - JOUR
TI - Asymmetric class-conditional routing in a federated quantum mixture-of-experts improves imbalanced intrusion detection in edge industrial IoT networks
AU - Amr H. Abdelhaliem
AU - Mohammed Tawfik
AU - Nedal Al Tamimi
AU - Islam S. Fathi
PY - 2026
DA - 2026/09/01
JO - Scientific Reports
DO - 10.1038/s41598-026-71421-5
UR - https://doi.org/10.1038/s41598-026-71421-5
AB - Intrusion detection systems (IDS) deployed in Edge Industrial Internet of Things (Edge-IIoT) environments face three critical and interrelated challenges: (i) extreme class imbalance, where tail-class attack categories may be outnumbered by benign traffic at ratios exceeding 700:1; (ii) competitive expert collapse in gating mechanisms relying on softmax normalization, which prevents sparse, class-conditional routing; and (iii) statistical heterogeneity across geographically distributed edge nodes with non-IID local traffic distributions. Existing federated learning solutions address these challenges in isolation, yielding suboptimal tail-class detection. We propose FedQMoE-IDS, a novel federated quantum mixture-of-experts framework that jointly resolves all three challenges through three synergistic innovations: (1) a class-balanced asymmetric focal loss with per-class focusing parameters γ _c that independently modulate head- and tail-class gradients via effective-number weighting; (2) a normalized sigmoid gating mechanism with auxiliary-loss-free dynamic bias load balancing, replacing softmax to achieve genuine sparse activation with exact zero weights and class-conditional expert routing; and (3) a selective federated aggregation strategy that partitions the parameter space into shared (FedDyn-aggregated CNN+KAN+classifier), locally retained (personalized gating networks), and periodically exchanged (variational quantum circuit experts) components. The three-stage MoE architecture cascades 1D-CNN feature extractors, variational quantum circuit (VQC) encoders operating in Hilbert space, and Kolmogorov–Arnold Network (KAN) spline experts, each governed by independent sigmoid top-K gates. We conduct experiments under a realistic non-IID federated setting with N=10 Edge-IIoT clients partitioned via a Dirichlet distribution ( α =0.3 ), and we compare against parameter-matched classical baselines (deeper CNN and softmax-gated MoE), personalized federated MoE (FedMoE, pFedMoE), and federated class-imbalance methods. Comprehensive experiments on UNSW-NB15, Edge-IIoTset, and CIC-IDS2017 with five-seed evaluation and Bonferroni-corrected Wilcoxon signed-rank tests demonstrate that FedQMoE-IDS achieves 99.20% accuracy and 98.40% macro F1-score on UNSW-NB15, and 99.80% accuracy on Edge-IIoTset—surpassing recent state-of-the-art methods including centralized deep learning, federated LSTM, and transformer-based IDS. All improvements are statistically significant ( p < 0.05 ). The full source code and configuration files are publicly available to enable independent reproduction.
SN - 2045-2322
ER -