Deep Sequence-to-Sequence Models for GNSS Spoofing Detection

2025-10-22

AI Summary

To address the challenge of real-time detection of GNSS signal spoofing attacks, this paper proposes an end-to-end online detection method based on the Transformer architecture. The approach introduces an early-input fusion strategy to jointly model heterogeneous time-series signals—including carrier-to-noise ratio (C/N₀) and pseudorange residuals—thereby enhancing cross-signal dependency learning without manual feature engineering. The model is trained on a large-scale, globally randomized spoofing dataset synthesized via high-fidelity GNSS signal simulation. Experimental results demonstrate a detection error rate of only 0.16% in simulated environments—substantially outperforming conventional LSTM-based and state-of-the-art baseline methods. The proposed solution achieves high accuracy, strong generalization across diverse spoofing scenarios, and low inference latency (<100 ms), making it suitable for real-time, deployable GNSS security applications.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Adversarial Attacks & Robustness
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Security and Privacy: Data transparency and provenance
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

We present a data generation framework designed to simulate spoofing attacks and randomly place attack scenarios worldwide. We apply deep neural network-based models for spoofing detection, utilizing Long Short-Term Memory networks and Transformer-inspired architectures. These models are specifically designed for online detection and are trained using the generated dataset. Our results demonstrate that deep learning models can accurately distinguish spoofed signals from genuine ones, achieving high detection performance. The best results are achieved by Transformer-inspired architectures with early fusion of the inputs resulting in an error rate of 0.16%.

Problem

• Detecting GNSS spoofing attacks using deep sequence models
• Simulating global spoofing scenarios through data generation
• Achieving high accuracy in online spoofing signal detection

Innovation

• Simulates spoofing attacks via global data generation framework
• Uses LSTM and Transformer models for online spoofing detection
• Transformer with early fusion achieves 0.16% error rate