EUVIMEDEUVIMED entdecken
Crossref

BENIGN-AWARE HISTOGRAM GRADIENT BOOSTING FOR MALICIOUS IOT NETWORK TRAFFIC DETECTION

Mohd Noor Derahman, Zezheng Qin, Azizol Abdullah, Shafinah Kamarudin

Journal of Information System and Technology Management · 30.03.2026 · 11 (42) · 337

DOI: 10.35631/jistm.1142020 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Information System and Technology Management, online erschienen am 30.03.2026. Verfasst von Mohd Noor Derahman und 3 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Detecting malicious traffic in Internet of Things (IoT) networks remains challenging because flow distributions are highly skewed, attack behaviours evolve quickly, and practical deployments must balance accuracy with computational cost. This study evaluates five classical machine learning models on IoT-23 and CICIoT2023 under multiple sample sizes and preprocessing settings. The experimental design includes 1,000, 5,000, 10,000, and 50,000-record subsets, median imputation, five-fold stratified cross-validation, explicit hyperparameter tuning, SMOTE-based imbalance analysis, and training and inference cost measurement. In addition to the five baseline models, the study introduces a benign-aware histogram gradient boosting variant (BA-HGB) that applies tuned cost- sensitive weighting to the minority benign class without synthetic data generation. On CICIoT2023, BA-HGB achieved the best five-fold macro- F1 score relative to the baseline models on the 10,000-sample benchmark (0.8898 +/- 0.0153), the best macro-F1 at 50,000 samples (0.8996 +/- 0.0038), and the highest ROC-AUC (0.9971 +/- 0.0003). An ablation in- side the HGB family further showed that all HGB variants outperformed the RF and GB baselines, whereas SMOTE consistently reduced both macro-F1 and benign-class F1. These results support the generalizability of the findings and show that histogram-based boosting is a strong practical direction for IoT intrusion detection, while imbalance handling mainly changes the accuracy-stability trade-off within that family.

Zitieren

APA

Derahman, M. N., Qin, Z., Abdullah, A., & Kamarudin, S. (2026). BENIGN-AWARE HISTOGRAM GRADIENT BOOSTING FOR MALICIOUS IOT NETWORK TRAFFIC DETECTION. Journal of Information System and Technology Management, 11(42), 337. https://doi.org/10.35631/jistm.1142020

Vancouver

Derahman MN, Qin Z, Abdullah A, Kamarudin S. BENIGN-AWARE HISTOGRAM GRADIENT BOOSTING FOR MALICIOUS IOT NETWORK TRAFFIC DETECTION. Journal of Information System and Technology Management. 2026;11(42):337. doi:10.35631/jistm.1142020

BibTeX
@article{Derahman2026,
  author = {Derahman, Mohd Noor and Qin, Zezheng and Abdullah, Azizol and Kamarudin, Shafinah},
  title = {BENIGN-AWARE HISTOGRAM GRADIENT BOOSTING FOR MALICIOUS IOT NETWORK TRAFFIC DETECTION},
  journal = {Journal of Information System and Technology Management},
  year = {2026},
  volume = {11},
  number = {42},
  pages = {337},
  doi = {10.35631/jistm.1142020}
}
Kostenlos starten →