2D-AEF: Low-Latency Sparse Expert Routing for Network Intrusion Detection
Authors:
Preprint
- 12 June 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Network intrusion detection systems must operate under strict latency constraints while maintaining reliable detection performance across heterogeneous traffic patterns. Traditional ensemble methods often improve predictive performance but require multiple model evaluations during inference, increasing computational costs. This paper presents 2D-AEF, a two-stage adaptive framework for network intrusion detection based on sparse conditional computation. A shallow decision-tree gatekeeper routes each traffic sample to a class-specialized expert selected through an offline search over model–feature subset pairs. Unlike conventional ensembles, only one expert is activated during inference, reducing computational overhead. The proposed framework was evaluated on UNSW-NB15 binary, UNSW-NB15 multi-class, and leakage-controlled CIC-IDS2018 robust scenarios. Experimental comparisons included strong standalone baselines and ensemble methods based on hard voting, soft voting, and stacking. Across ten random seeds, 2D-AEF achieved macro-F1 scores of 0.890, 0.461, and 0.871 on the three scenarios, respectively. While not consistently outperforming the strongest classifiers in predictive performance, the proposed framework reduced median inference latency by factors ranging from 6.5x to 12.5x compared with stacking. The results demonstrate that class-conditioned sparse routing provides an effective strategy for balancing detection performance and inference efficiency in network intrusion detection systems.Keywords
This publication has 14 references indexed in Scilit:
- A Comprehensive Survey on Ensemble Learning-Based Intrusion Detection Approaches in Computer NetworksIEEE Access, 2023
- Addressing the class imbalance problem in network intrusion detection systems using data resampling and deep learningThe Journal of Supercomputing, 2023
- Dynamic Mixture of Experts Models for Online PredictionTechnometrics, 2022
- A Novel Ensemble Framework for an Intelligent Intrusion Detection SystemIEEE Access, 2021
- An Ensemble-Based Scalable Approach for Intrusion Detection Using Big Data FrameworkBig Data, 2021
- Intrusion Detection System Based on Fast Hierarchical Deep Convolutional Neural NetworkIEEE Access, 2021
- HDEC: A Heterogeneous Dynamic Ensemble Classifier for Binary DatasetsComputational Intelligence and Neuroscience, 2020
- Performance Analysis of Intrusion Detection Systems Using a Feature Selection Method on the UNSW-NB15 DatasetJournal of Big Data, 2020
- A survey and analysis of intrusion detection models based on CSE-CIC-IDS2018 Big DataJournal of Big Data, 2020
- XGBoost2016