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

2025-07-15

AI Summary

Stealthy drift-avoiding spoofing attacks against UAV GNSS navigation—difficult to detect via conventional signal-level methods—induce significant detection latency, compromising flight safety. Method: This paper proposes a real-time Bayesian online change-point detection (BOCPD) framework that innovatively integrates value estimation from a reinforcement learning critic network with GNSS pseudorange time-series modeling, enabling low-latency detection of subtle, gradual navigational deviations without requiring large-sample accumulation. Contribution/Results: Experimental evaluation demonstrates that the proposed method significantly outperforms conventional GNSS detectors, semi-supervised frameworks, and the Page-Hinkley test: detection accuracy is improved, with false positive and false negative rates reduced by 32.7% and 41.5%, respectively. The approach enables rapid emergency response initiation at attack onset, thereby enhancing UAV robustness and autonomous recovery capability in adversarial environments.

Technology Category

• Intelligent Robots: State Estimation
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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.

Problem

• Detect drift-evasive GNSS spoofing in UAV navigation
• Identify subtle behavioral deviations using RL critic networks
• Improve detection accuracy and reduce false alarm rates

Innovation

• Bayesian online change point detection for spoofing
• Monitors RL critic network temporal shifts
• Outperforms traditional GNSS spoofing detectors