EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Immune-Edge: Adaptive Constrained Distillation with Runtime Self-Healing for Adversarially Robust Edge Intrusion Detection in 5G Networks

Hassan Jawad, Altaf Muhammad, Wooseong Kim

Electronics · 07.11.2026 · 15 (21) · 5173

DOI: 10.3390/electronics15215173 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 07.11.2026. Verfasst von Hassan Jawad und 2 weiteren Autor:innen. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Gachon University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural intrusion detection systems (IDSs) on fifth-generation (5G) edge hardware face three pressures: adversaries crafting perturbations to evade detection, device budgets capping inference latency and model size, and traffic that drifts post-deployment. We present Immune-Edge, a three-tier framework that formulates the recovery of a deployed IDS model under drift as constrained re-distillation from a frozen, adversarially trained teacher. The core algorithm enforces latency and model-size limits as hard constraints via primal–dual optimization, with a penalty strength that adapts to the observed constraint violation instead of a fixed penalty coefficient. A feedback loop tied to the student’s false-positive rate (FPR) adjusts adversarial loss weight automatically, keeping robustness and accuracy balanced without manual tuning. When sustained FPR elevation signals distribution shift, a self-healing loop triggers re-distillation at the Multi-access Edge Computing (MEC) node from the frozen teacher, without device-side backpropagation or cloud retraining. On CIC IoT-DIAD 2024 and ToN_IoT under a runtime drift protocol, Immune-Edge outperforms the best non-healing baseline in adversarial accuracy by 9.2% and 13.2% (relative), reduces FPR by 83% and 84%, and recovers below pre-drift FPR in a single healing event under 2 ms inference latency. These results show that a drifted edge IDS model can be recovered by constrained re-distillation from a frozen, adversarially trained teacher without losing robustness or exceeding the device budget.

Förderung

  • Gachon University

Zitieren

APA

Jawad, H., Muhammad, A., & Kim, W. (2026). Immune-Edge: Adaptive Constrained Distillation with Runtime Self-Healing for Adversarially Robust Edge Intrusion Detection in 5G Networks. Electronics, 15(21), 5173. https://doi.org/10.3390/electronics15215173

Vancouver

Jawad H, Muhammad A, Kim W. Immune-Edge: Adaptive Constrained Distillation with Runtime Self-Healing for Adversarially Robust Edge Intrusion Detection in 5G Networks. Electronics. 2026;15(21):5173. doi:10.3390/electronics15215173

BibTeX
@article{Jawad2026,
  author = {Jawad, Hassan and Muhammad, Altaf and Kim, Wooseong},
  title = {Immune-Edge: Adaptive Constrained Distillation with Runtime Self-Healing for Adversarially Robust Edge Intrusion Detection in 5G Networks},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {21},
  pages = {5173},
  doi = {10.3390/electronics15215173}
}
Kostenlos starten →