EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LEAF: A Lightweight, Explainable, and Federated Attention Model for Trustworthy 5G Intrusion Detection Under a Leakage-Aware Benchmark

Humam Ali Hameed, Sarmad Khalil Ibrahim

Journal of Cybersecurity and Privacy · 15.11.2026 · 6 (6) · 205

DOI: 10.3390/jcp6060205 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Cybersecurity and Privacy, online erschienen am 15.11.2026. Verfasst von Humam Ali Hameed und 1 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep models report accuracies at or above 99% on the 5G-NIDD benchmark, yet much of that headline reflects how the data are prepared. We show that two forms of leakage (a random split that mixes capture sessions, and identifier-like features that stand in for the label) inflate results, rebuild the protocol so neither can help, and rerun the reproducible baselines under both protocols. On the clean benchmark we introduce LEAF, a lightweight per-flow attention model whose feature gate and attention pool double as inherent explanations and which performs no intra-window mixing because every mixer we tried lowers macro-F1. LEAF is first on accuracy (98.99%), macro-accuracy, and Matthews correlation coefficient (0.985), and statistically second by a small margin on macro-F1 (97.92%). It comes with inherent explanations about 1800× faster than SHapley Additive exPlanations (SHAP), federated training that stays near 99% on non-identically distributed clients and resists Byzantine poisoning to 25% malicious clients with robust aggregation, and lossless 8-bit integer quantization that cuts memory threefold, to about 29 KB, with sub-millisecond inference. We also report where LEAF loses, namely on cross-extractor transfer, on a novel control-plane attack, and under gradient input perturbations.

Zitieren

APA

Hameed, H. A., & Ibrahim, S. K. (2026). LEAF: A Lightweight, Explainable, and Federated Attention Model for Trustworthy 5G Intrusion Detection Under a Leakage-Aware Benchmark. Journal of Cybersecurity and Privacy, 6(6), 205. https://doi.org/10.3390/jcp6060205

Vancouver

Hameed HA, Ibrahim SK. LEAF: A Lightweight, Explainable, and Federated Attention Model for Trustworthy 5G Intrusion Detection Under a Leakage-Aware Benchmark. Journal of Cybersecurity and Privacy. 2026;6(6):205. doi:10.3390/jcp6060205

BibTeX
@article{Hameed2026,
  author = {Hameed, Humam Ali and Ibrahim, Sarmad Khalil},
  title = {LEAF: A Lightweight, Explainable, and Federated Attention Model for Trustworthy 5G Intrusion Detection Under a Leakage-Aware Benchmark},
  journal = {Journal of Cybersecurity and Privacy},
  year = {2026},
  volume = {6},
  number = {6},
  pages = {205},
  doi = {10.3390/jcp6060205}
}
Kostenlos starten →