Toward Adversarial Robustness Network Intrusion Detection Based on Multi-Model Ensemble Approach
Sensors · 17.04.2026 · 26 (8) · 2478
DOI: 10.3390/s26082478 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 17.04.2026. Verfasst von Thi-Thu-Huong Le und 3 weiteren Autor:innen. Beteiligte Einrichtung: Blockchain Platform Research Center, Pusan National University, Busan 46241, Republic of Korea. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: This research was supported by the National Research Council of Science & Technology(NST) grant funded by the Korea government (MSIT) (No. GTL24031-800) and wa….
Abstract (Originalsprache)
Machine learning-based network intrusion detection systems (NIDSs) remain vulnerable to adversarial manipulation, but the robustness literature for tabular NIDS data is still dominated by single-model, single-dataset, and non-adaptive evaluations. In this paper, we reposition the manuscript as a comparative robustness study of a four-component defense pipeline rather than as a claim of a universal defense primitive. We evaluate XGBoost, LightGBM, TabNet, and Residual MLP on RT_IOT2022 and Web_IDS23 under standard attacks, representative constrained/adaptive attacks, component-wise ablations, sample-fraction sensitivity, repeated-run significance tests, per-class F1 analysis, and computational-overhead measurements. The results show strong dataset and architecture dependence. On RT_IOT2022, tree-based models close most of the robustness gap under strong attacks but often only after large clean-accuracy reductions; Residual MLP achieves a more favorable balance, while the full defense stack over-regularizes TabNet. On Web_IDS23, aggregate robustness-gap reduction remains positive, yet simpler baselines such as adversarial-training-only or ensemble-only configurations frequently outperform the full four-stage pipeline in absolute clean/attack accuracy. Across both datasets, median filtering is the most fragile component: larger filter windows substantially degrade both clean and attacked accuracy, whereas contamination rate, anomaly-mixing weight, and ensemble size are comparatively stable. Representative constrained/adaptive evaluations reduce performance only modestly relative to standard FGSM/PGD, but per-class and overhead analyses show that minority-class collapse and training cost remain important deployment limitations. These findings support a more cautious conclusion: adversarial defense for tabular NIDS is validation driven and dataset specific, and the full defense stack should not be treated as a universal default.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Blockchain Platform Research Center, Pusan National University, Busan 46241, Republic of Korea.
- School of Computer Science and Engineering, Pusan National University, Busan 46241, Republic of Korea.
ORCID-Profile: Thi-Thu-Huong Le, Jaehan Cho, Dawit Shin, Howon Kim
Förderung
- This research was supported by the National Research Council of Science & Technology(NST) grant funded by the Korea government (MSIT) (No. GTL24031-800) and wa…
Zitieren
APA
Le, T. T., Cho, J., Shin, D., & Kim, H. (2026). Toward Adversarial Robustness Network Intrusion Detection Based on Multi-Model Ensemble Approach. Sensors, 26(8), 2478. https://doi.org/10.3390/s26082478
Vancouver
Le TT, Cho J, Shin D, Kim H. Toward Adversarial Robustness Network Intrusion Detection Based on Multi-Model Ensemble Approach. Sensors. 2026;26(8):2478. doi:10.3390/s26082478
BibTeX
@article{Le2026,
author = {Le, Thi-Thu-Huong and Cho, Jaehan and Shin, Dawit and Kim, Howon},
title = {Toward Adversarial Robustness Network Intrusion Detection Based on Multi-Model Ensemble Approach},
journal = {Sensors},
year = {2026},
volume = {26},
number = {8},
pages = {2478},
doi = {10.3390/s26082478}
}
EUVIMED