NIDD-enabled lightweight intrusion detection for effective DDoS mitigation in 5G and beyond

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F25%3A10259124" target="_blank" >RIV/61989100:27240/25:10259124 - isvavai.cz</a>

Result on the web

<a href="https://www.nature.com/articles/s41598-025-26056-3" target="_blank" >https://www.nature.com/articles/s41598-025-26056-3</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1038/s41598-025-26056-3" target="_blank" >10.1038/s41598-025-26056-3</a>

Result language

angličtina

Original language name

NIDD-enabled lightweight intrusion detection for effective DDoS mitigation in 5G and beyond

Original language description

With the introduction of 5G technology, wireless communication is expected to undergo revolutionary changes that will allow high-speed connectivity and scalability. Though 5G networks have the potential to be revolutionary, they also pose new challenges in ensuring the security and integrity of data transfer, especially in Non-IP Data Delivery (NIDD) scenarios. The need for robust anomaly detection systems becomes even more critical in this scenario to safeguard IoT and other reliable networks. Anomaly detection has been the subject of much research in network contexts, as it is crucial for identifying hostile activity, system failures, and odd behavior. The growing dependence on technologies, particularly with the advent of 5G and its potential to connect nearly everything, has made it imperative to investigate intelligent and efficient techniques that ensure network availability, secrecy, and integrity. To address the botnet infiltration, DDoS mitigation, and other incursions in 5G networks, a novel lightweight intrusion detection model is proposed for 5G and beyond networks, which uses the 5GNIDD dataset in the experiments. The proposed model is powered by a robust prepossessing model, which uses Gini Importance for feature selection and state-of-the-art classifiers, namely, AdaBoost, Easy Ensemble, GRU, 1D-CNN, LSTM, and hybrid CNN-LSTM for classification. Two different case studies with k-best features are driven in experiments showcasing the effect of the curse of dimensionality on precision. The model has obtained 99.64% accuracy and a 0.9830 precision using 1D-CNN and a hybrid LSTM-CNN model.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

20200 - Electrical engineering, Electronic engineering, Information engineering

Project

—

Continuities

O - Projekt operacniho programu

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Scientific Reports

ISSN

2045-2322

e-ISSN

2045-2322

Volume of the periodical

15

Issue of the periodical within the volume

1

Country of publishing house

GB - UNITED KINGDOM

Number of pages

27

Pages from-to

nestránkováno

UT code for WoS article

001628513300001

EID of the result in the Scopus database

—