MétaCan
Menu
Back to cohort

BERT-Driven Intrusion Detection System for 5G Core Security

2025· article· W7127924620 on OpenAlexaff
Yathusan Thulasinathan, Glaucio H.S. Carvalho, Isaac Woungang

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicNetwork Security and Intrusion Detection
Canadian institutionsToronto Metropolitan UniversityBrock University
Fundersnot available
KeywordsTestbedSoftware deploymentIntrusion detection systemSession (web analytics)ScalabilityAuthentication (law)Denial-of-service attackCore (optical fiber)

Abstract

fetched live from OpenAlex

The proliferation of $\mathbf{5 G}$ networks introduces a highly dynamic and virtualized service-based architecture, increasing the attack surface of core network components. Securing the 5 G Core requires accurate and scalable intrusion detection mechanisms. This work proposes a BERT-based Intrusion Detection System (IDS) designed to classify legitimate and malicious 5G Core communications. A cloud-native testbed was deployed using Free5GC, UERANSIM, and Kubernetes to emulate realistic 5 G core operations. Legitimate traffic was captured from user equipment (UE) authentication procedures, while malicious flows were generated from three control-plane attack scenarios: TCP SYN flooding, PFCP session deletion, and unauthorized NRF probing. Compared to baseline mod-els-LSTM and 1D CNN-LSTM-BERT achieved superior detection performance, attaining 100% accuracy, precision, recall, and F1-score. However, computational analysis indicated that BERT’s resource demands, including over 3 GB of GPU memory and 266.52 GFLOPs per inference, may limit deployment in constrained environments. Future work will investigate more computationally efficient BERT variants for practical deployment in cloud-native 5 G security frameworks.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.004
Threshold uncertainty score0.008

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0010.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0020.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.015
GPT teacher head0.253
Teacher spread0.237 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicNetwork Security and Intrusion DetectionFrench-language works237,207