OpenResearchAlpha

Electronics · 7 Nov 2026

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

Hassan Jawadh-index 0, Altaf Muhammad, Wooseong Kimh-index 23

0
Citations
no database records one yet
0
Citations in 2026
so far
23
Leading author's h-index
Wooseong Kim, in QAI's scholar index
0
References
works it cites, from open citation data

Citations by database

Each database indexes a different set of journals, preprints and books, so they are shown side by side rather than blended.

  • OpenCitations0
  • Crossref0

Citations per year

The current year is still counting.

  • 2026 so far0

Abstract

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.

What the data shows

  • No database records a citation yet, as is usual for a paper this new.
  • Wooseong Kim has the highest h-index among the authors (23).

Graph

This paper in the middle, its authors and their most-cited papers below, the papers it cites to the left and the papers citing it to the right. The timeline lays every paper out by year.

Citing paper shares an authorAuthor without a profileSize shows citations, or h-index for authors

Select a node for its details. Drag to pan, scroll to zoom, drag a node to move it.

Start with

Authors (3)

Each author's standing in QAI's scholar index: the works their ORCID iD is attached to, and for anyone whose ORCID record names a lab OpenResearch follows, their arXiv preprints matched by name and a shared co-author. Names are as printed on the paper.

ProfileMost-cited paper

Cited by 0 papers

Who cites this paper, from open citation data, with Crossref's record of each; the 100 newest when there are more.

0 shown
No citing papers for this filter.

References (0)

What it cites, from open citation data, with Crossref's record of each.

No references in the open citation data yet.