One-Class Classification as GLRT for Jamming Detection in Private 5G Networks

TL;DR

This paper introduces a CNN-based generalized likelihood ratio test (GLRT) detector for jamming attacks in private 5G networks, demonstrating effective detection through experimental validation with real and synthetic data.

Contribution

It presents a novel learning-based approach using CNNs to implement GLRT for jamming detection in 5G, with training on real and artificially generated datasets.

Findings

High detection accuracy on experimental data

Effective identification of various jamming signals

Demonstrated robustness in private 5G environments

Abstract

5G mobile networks are vulnerable to jamming attacks that may jeopardize valuable applications such as industry automation. In this paper, we propose to analyze radio signals with a dedicated device to detect jamming attacks. We pursue a learning approach, with the detector being a CNN implementing a GLRT. To this end, the CNN is trained as a two-class classifier using two datasets: one of real legitimate signals and another generated artificially so that the resulting classifier implements the GLRT. The artificial dataset is generated mimicking different types of jamming signals. We evaluate the performance of this detector using experimental data obtained from a private 5G network and several jamming signals, showing the technique's effectiveness in detecting the attacks.