Approaching Domain Generalization with Embeddings for Robust Discrimination and Recognition of RF Communication Signals

TL;DR

This paper introduces a novel embedding learning method for RF signal recognition that generalizes well to unseen real-world signals by training on synthetic data, enhancing robustness and reducing dependence on extensive real-world datasets.

Contribution

The paper presents a new approach to learn discriminative RF signal embeddings from synthetic data, improving generalization to unseen real-world signals.

Findings

Embeddings effectively discriminate unseen real RF signals.

Method reduces reliance on extensive real-world training data.

Demonstrates robustness in RF signal classification and anomaly detection.

Abstract

Radio frequency (RF) signal recognition plays a critical role in modern wireless communication and security applications. Deep learning-based approaches have achieved strong performance but typically rely heavily on extensive training data and often fail to generalize to unseen signals. In this paper, we propose a method to learn discriminative embeddings without relying on real-world RF signal recordings by training on signals of synthetic wireless protocols. We validate the approach on a dataset of real RF signals and show that the learned embeddings capture features enabling accurate discrimination of previously unseen real-world signals, highlighting its potential for robust RF signal classification and anomaly detection.