A Hybrid-Based PSO-Optimized CNN-LSTM Model for 5G Networks Intrusion Detection
DOI:
https://doi.org/10.19139/soic-2310-5070-4714Keywords:
5 G security, intrusion Detection, CNN-LSTM, Particle Swarm Optimization, Network Threats, Distribution Denial-of-Service (DDoS)Abstract
The escalating demand for 5G networks, driven by heightened connectivity and modern application needs,necessitates robust security solutions to counter threats like denial-of-service attacks. This study introduces two optimizedCNN-LSTM hybrid models for enhanced intrusion detection in 5G networks, leveraging the 5G-NIDD dataset. Byintegrating Particle Swarm Optimization (PSO) for hyperparameter tuning, the models achieve superior performance. Thefirst model attains training and validation accuracies of 89.98% and 90.10%, respectively, while the second model excels witha validation accuracy of 99.79% and a minimal loss of 0.0085. These results underscore the models’ exceptional accuracyand generalization in classifying malicious network activities, offering a potent solution for 5G security challenges.Downloads
Published
2026-10-31
How to Cite
Elanay, M., Bekhiet, A., & Gaber, A. (2026). A Hybrid-Based PSO-Optimized CNN-LSTM Model for 5G Networks Intrusion Detection. Statistics, Optimization & Information Computing. https://doi.org/10.19139/soic-2310-5070-4714
License
Copyright (c) 2026 Marwa Elanay, Ali Bekhiet, Amira Gaber
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
