Real-Time Bayesian Detection of Drift-Evasive GNSS Spoofing in Reinforcement Learning Based UAV Deconfliction

TL;DR

This paper presents a Bayesian online change point detection method that monitors RL critic values to detect stealthy GNSS spoofing attacks on UAVs in real-time, improving detection speed and accuracy.

Contribution

It introduces a novel temporal value-based detection framework using BOCPD to identify drift-evasive spoofing attacks more effectively than existing methods.

Findings

Outperforms conventional GNSS spoofing detectors in accuracy

Achieves lower false-positive and false-negative rates

Detects subtle spoofing attacks faster in real-time

Abstract

Autonomous unmanned aerial vehicles (UAVs) rely on global navigation satellite system (GNSS) pseudorange measurements for accurate real-time localization and navigation. However, this dependence exposes them to sophisticated spoofing threats, where adversaries manipulate pseudoranges to deceive UAV receivers. Among these, drift-evasive spoofing attacks subtly perturb measurements, gradually diverting the UAVs trajectory without triggering conventional signal-level anti-spoofing mechanisms. Traditional distributional shift detection techniques often require accumulating a threshold number of samples, causing delays that impede rapid detection and timely response. Consequently, robust temporal-scale detection methods are essential to identify attack onset and enable contingency planning with alternative sensing modalities, improving resilience against stealthy adversarial manipulations. This study explores a Bayesian online change point detection (BOCPD) approach that monitors temporal shifts in value estimates from a reinforcement learning (RL) critic network to detect subtle behavioural deviations in UAV navigation. Experimental results show that this temporal value-based framework outperforms conventional GNSS spoofing detectors, temporal semi-supervised learning frameworks, and the Page-Hinkley test, achieving higher detection accuracy and lower false-positive and false-negative rates for drift-evasive spoofing attacks.