Data-driven classification of low-power communication signals by an unauthenticated user using a software-defined radio

TL;DR

This paper demonstrates that an unauthenticated user can classify LoRa signals using neural networks by analyzing their frequency patterns, revealing vulnerabilities in low-power communication systems.

Contribution

It introduces a novel method for classifying LoRa signals based on frequency patterns, highlighting security vulnerabilities in low-power wireless protocols.

Findings

Neural networks can accurately classify LoRa signals based on frequency features.

The method can identify bandwidth and spreading factor from raw signals.

Vulnerabilities in LoRa protocol to unauthenticated signal inference are demonstrated.

Abstract

Many large-scale distributed multi-agent systems exchange information over low-power communication networks. In particular, agents intermittently communicate state and control signals in robotic network applications, often with limited power over an unlicensed spectrum, prone to eavesdropping and denial-of-service attacks. In this paper, we argue that a widely popular low-power communication protocol known as LoRa is vulnerable to denial-of-service attacks by an unauthenticated attacker if it can successfully identify a target signal's bandwidth and spreading factor. Leveraging a structural pattern in the LoRa signal's instantaneous frequency representation, we relate the problem of jointly inferring the two unknown parameters to a classification problem, which can be efficiently implemented using neural networks.