Toward Resilient 5G Networks: Comparative Analysis of Federated and Centralized Learning for RF Jamming Detection

2026-05-03

AI Summary

This study addresses the privacy risks inherent in centralized approaches to interference attack detection in 5G radio frequency (RF) domains by proposing the first federated learning–based interference detection framework. The proposed method leverages in-phase and quadrature (IQ) samples extracted by user equipment from synchronization signal blocks and employs the Federated Averaging (FedAvg) algorithm to collaboratively train a one-dimensional convolutional neural network, enabling effective interference identification without sharing raw RF data. Experimental results demonstrate that the framework achieves 97% accuracy and F1 score on the interference detection task, significantly outperforming centralized baseline models such as multilayer perceptrons (MLPs) and support vector machines (SVMs), thereby enhancing detection performance while preserving user data privacy.

Abstract

Jamming attacks are proliferating and pose a significant threat to the security of 5G and beyond networks. These attacks target 5G radio frequency (RF) domain and can disrupt the communication in wireless networks. While conventional machine learning and deep learning approaches demonstrate its potential for jamming detection, they typically require centralized data collection, compromising the privacy of user equipment (UEs). This work proposes a federated learning (FL)-based jamming detection framework that operates on over-the-air In-phase and Quadrature (IQ) samples extracted from Synchronization Signal Blocks (SSBs) in the RF domain. The framework enables collaborative model training across multiple UEs without sharing raw RF signal data. We adopt Federated Averaging (FedAvg) algorithm to train a 1D convolutional neural network (1DCNN) for effective detection of attacks. Numerical results demonstrate that the proposed FL framework achieves 97% accuracy and 97% F1-score, outperforming centralized baselines including MLP, 1DCNN, SVM, and logistic regression, while preserving the data privacy of all participating UEs

Problem

• jamming detection
• 5G networks
• federated learning
• RF security
• privacy preservation

Innovation

• Federated Learning
• RF Jamming Detection
• 5G Security
• Privacy-Preserving
• 1D CNN