Jamming Detection in Cell-Free MIMO with Dynamic Graphs

TL;DR

This paper introduces a novel jamming detection method for cell-free MIMO systems using dynamic graph modeling and graph neural networks, effectively identifying malicious interference in complex, time-varying wireless network topologies.

Contribution

It proposes a new framework combining dynamic graph modeling with GCNs and Transformers for jamming detection in cell-free MIMO, addressing the challenge of evolving network topologies.

Findings

High detection accuracy in simulated scenarios

Effective identification of jamming under various conditions

Robust performance with dynamic network changes

Abstract

Jamming attacks pose a critical threat to wireless networks, particularly in cell-free massive MIMO systems, where distributed access points and user equipment (UE) create complex, time-varying topologies. This paper proposes a novel jamming detection framework leveraging dynamic graphs and graph convolutional neural networks (GCN) to address this challenge. By modeling the network as a dynamic graph, we capture evolving communication links and detect jamming attacks as anomalies in the graph evolution. A GCN-Transformer-based model, trained with supervised learning, learns graph embeddings to identify malicious interference. Performance evaluation in simulated scenarios with moving UEs, varying jamming conditions and channel fadings, demonstrates the method's effectiveness, which is assessed through accuracy and F1 score metrics, achieving promising results for effective jamming detection.