The growing reliance on global navigation satellite systems (GNSS) for critical applications makes them a prime target for spoofing attacks. We propose a machine learning (ML)based blind authentication framework that integrates GNSS signals with low Earth orbit (LEO) signals of opportunity (SOOP), whose positions are not known a priori. Our approach leverages the consistency between GNSS and LEO-derived measurements, with a focus on Doppler shift, to detect spoofing attacks. We introduce a novel SOOP transmitter identification process based on pseudorange and Doppler shift residuals and evaluate multiple ML-based detectors, including support vector machines (SVM), one class SVM (OCSVM), and neural network (NN). Simulation results demonstrate that the proposed framework significantly improves spoofing detection performance, even with limited trusted measurements.
ML-Based Blind Authentication with LEO Signals of Opportunity
Ardizzon, Francesco;Crosara, Laura;Laurenti, Nicola
2025
Abstract
The growing reliance on global navigation satellite systems (GNSS) for critical applications makes them a prime target for spoofing attacks. We propose a machine learning (ML)based blind authentication framework that integrates GNSS signals with low Earth orbit (LEO) signals of opportunity (SOOP), whose positions are not known a priori. Our approach leverages the consistency between GNSS and LEO-derived measurements, with a focus on Doppler shift, to detect spoofing attacks. We introduce a novel SOOP transmitter identification process based on pseudorange and Doppler shift residuals and evaluate multiple ML-based detectors, including support vector machines (SVM), one class SVM (OCSVM), and neural network (NN). Simulation results demonstrate that the proposed framework significantly improves spoofing detection performance, even with limited trusted measurements.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.