City Research Online

Abstract

Rogue Base Station (RBS) is a persistent security threat in 5G and 5G beyond networks, which exploits radio access procedures to attract user equipment through abnormal signal behavior. This paper introduces RBS-MLP, a hybrid Computational Intelligence (CI) framework that integrates datadriven learning with state-based reasoning to safely detect RBSs early and reliably. Unlike existing client- or cloud-based solutions, RBS-MLP operates entirely within the network, enabling finergrained detection without requiring modifications to user equipment. This framework incorporates novel engineered temporal signal features, including the Rate of Change of Received Signal (RoCH), and a probation-based finite state machine to capture both short-term dynamics and long-term consistency in base station behavior. Under realistic mobility scenarios, a multilayer perceptron classifier is trained and tested on time-series measurement reports across multiple generated datasets and signal window sizes to identify legitimate entities and rogue entities. In this study, the proposed approach is evaluated by analyzing more than 200,000 measurements collected in a large-scale 5G vehicle platooning scenario. Experimental results demonstrate detection accuracy of up to 99.9%, with consistently low false positive rates while maintaining low computational overhead suitable for real-time deployment. RBS-MLP provides a scalable, efficient, and standards-aligned baseline to identify RBS in 5G intelligent transportation systems environments. In addition to being compliant with 3GPP Release 18, this framework is compatible with emerging RAN architectures, making it suitable for 5G services that require low latency.

Publication Type:	Other (Preprint)
Additional Information:	This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.
Publisher Keywords:	5G mobile networks, computational intelligence, machine learning, and rogue base station detection
Subjects:	H Social Sciences > HE Transportation and Communications Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > TA Engineering (General). Civil engineering (General)
Departments:	School of Science & Technology School of Science & Technology > Department of Computer Science
SWORD Depositor:	Symplectic Administrator

Export

Downloads