ITSC 2025 Paper Abstract

Paper WE-EA-T13.2

Wang, Siqi (Beijing Jiaotong University), Liu, Jiang (Beijing Jiaotong University), Cai, Baigen (Beijing Jiaotong University), Lu, Debiao (Beijing Jiaotong University), Jiang, Wei (Beijing Jiaotong University)

Simultaneous Detection and Compensation against GNSS Spoofing for Factor Graph-Based Train Localization

Scheduled for presentation during the Regular Session "S13b-Localization, Mapping, and Sensing for Robust Navigation in ITS" (WE-EA-T13), Wednesday, November 19, 2025, 13:50−14:10, Stradbroke

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 19, 2025

Keywords Cybersecurity in Autonomous and Connected Vehicle Systems, Safety Verification and Validation Methods for Autonomous Vehicle Technologies, Sensor Integration and Calibration for Accurate Localization in Dynamic Road Conditions

Abstract

The growing use of Global Navigation Satellite Systems (GNSS) in rail systems raises significant cybersecurity concerns. Potential threats from the GNSS spoofing interference, which can severely degrade GNSS performance or cause complete failures, may hinder resilient train localization. To mitigate spoofing interference, this paper introduces a simultaneous detection and compensation framework against GNSS spoofing, which integrates the multi-task Spiking Neural Network (SNN) model and Factor Graph Optimization (FGO) technique. A multi-task SNN model is designed to jointly detect spoofing and predict Spoofing-induced Measurement Errors (SIMEs), which are then used to compensate for the identified spoofed measurements and mitigate the impact on state estimation. A Gaussian Mixture Model (GMM) is employed to model the measurement noise, relieving environmental and spoofing-related impacts on the Weighted Least Squares (WLS) calculation. In addition, FGO is employed to fuse multi-sensor data, further enhancing the accuracy, stability, and reliability of multi-source fusion-based localization. Experiments based on field-collected data and a spoofing injection platform demonstrate the anti-spoofing ability of the proposed solution. It guarantees the seamless and transparent handover of the train localization system under the spoofing interference condition, thereby enabling autonomous and reliable localization for railway applications.