Researchers have developed a federated learning framework to detect RF jamming attacks in 5G networks. This approach trains a 1D convolutional neural network using In-phase and Quadrature samples from Synchronization Signal Blocks, allowing collaborative model training across user equipment without sharing raw signal data. The federated learning method achieved 97% accuracy and F1-score, outperforming centralized machine learning models while preserving user privacy. AI
Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →
IMPACT Enhances 5G network security by enabling privacy-preserving, collaborative detection of jamming attacks.
RANK_REASON Academic paper presenting a novel federated learning approach for RF jamming detection in 5G networks. [lever_c_demoted from research: ic=1 ai=1.0]