RFI and Jamming Detection in Antenna Arrays with an LSTM Autoencoder

TL;DR

This paper introduces a novel method combining Fourier imaging and an LSTM autoencoder to detect RFI and jamming in antenna arrays, achieving high performance without prior knowledge of interference signals.

Contribution

It presents a new approach that uses spatial localization and deep learning for RFI and jamming detection, differing from traditional statistical and AI methods.

Findings

High detection accuracy across various interference power levels

No prior knowledge required of RFI or jamming signals

Effective localization of interference sources using Fourier imaging

Abstract

Radio frequency interference (RFI) and malicious jammers are a significant problem in our wireless world. Detecting RFI or jamming is typically performed with model-based statistical detection or AI-empowered algorithms that use an input baseband data or time-frequency representations like spectrograms. In this work we depart from the previous approaches and we leverage data in antenna array systems. We use Fourier imaging to localize spatially the sources and then deploy a deep LSTM autoencoder that detects RFI and jamming as anomalies. Our results for different power levels of the RFI/jamming sources, and the signal of interest, reveal that our detector offers high performance without needing any pre-existing knowledge regarding the RFI or jamming signal.