Statistical method improves jamming detection across diverse 5G networks
O-RAN-Native Jamming Detection Under Network Heterogeneity
Machine Learning
Summary
Cellular networks can be disrupted by radio jamming, which makes signals unreliable. The authors propose a new statistical method to detect jamming using standard network reports without needing special hardware. Their method works well even when the network environment changes and when there is no prior labeled data available. They show it performs better than typical machine learning approaches when faced with new conditions. This approach can be continuously improved with collected data and integrated into existing network management systems.
What this means in practice
- •For telecom network operators: Detect RF jamming across various 5G network setups using existing O-RAN telemetry without needing special hardware.
- •For wireless security teams: Deploy a rapid-start method to identify jamming attacks early when no labeled data is available, improving response times.
Authors
Sneihil Gopal, Fernando J. Cintrón, Richard A. Rouil
Abstract
Radio-frequency jamming threatens cellular network operations in contested environments. The Open Radio Access Network (O-RAN) architecture exposes per-User Equipment (UE) telemetry through the E2 interface, enabling Key Performance Indicator (KPI)-based jamming detection without proprietary hardware. However, operational deployment demands detection methods that generalize across heterogeneous networks. We propose a Statistical Ensemble Method (SEM) combining adaptive Median Absolute Deviation (MAD)-based baseline detection, count-based anomaly detection, and abrupt change detection through a weighted voting system. SEM operates in two modes: a cold-start mode requiring no labeled data for immediate deployment, and a supervised mode where parameters are refined offline via grid search as labeled data accumulates. We evaluate SEM against five machine learning (ML) classifiers and five deep learning (DL) sequence models using approximately 25 hours of testbed data comprising logs from eight heterogeneous 5G environments, employing both single-environment and multi-environment leave-one-out (LOO) validation. Our analysis indicates that under conditions not encountered during training (distribution shift), learning-based models tend to lose recall and miss jamming events, whereas SEM, even in cold-start mode, maintains detection capabilities at the cost of false alarms. Furthermore, SEM's parameter optimization can be mapped to O-RAN's Non-RT RIC as an rApp for continuous refinement, allowing operators to transition to learning-based alternatives once corpus coverage is sufficient.