Gao, Jin (Beijing Jiaotong University), Liu, Jiang (Beijing Jiaotong University), Cai, Baigen (Beijing Jiaotong University), Wang, Jian (Beijing Jiaotong University)

Risk Level Estimation of GNSS Spoofing Interference Using an Enhanced SE-DenseNet Model

Scheduled for presentation during the Regular Session "Advanced Vehicle Safety Systems II" (ThAT8), Thursday, September 26, 2024, 10:50−11:10, Salon 16

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on October 8, 2024

Abstract

Utilizing Global Navigation Satellite System (GNSS) in railway train positioning is a viable solution for a train-centric railway systems, like the train control system. However, the GNSS spoofing interference may pose a serious threat to the performance and service availability of train positioning. Hence, identification and evaluation of the spoofing interference risk would be of great necessity and significance to trigger specific spoofing suppression measures. Therefore, we propose an enhanced SE-DenseNet modeling solution for estimating the risk level of GNSS spoofing interference. Specific GNSS features are extracted within both the observation domain and navigation calculation domain. With the evaluation of the Spoofing Risk Index (SRI) with respect to the feature set, the sample datasets are generated, and the enhanced DenseNet model integrating the Squeeze-and-Excitation (SE) attention mechanism module realizes the data-driven estimation of the spoofing risk level. The validation of the proposed solution is carried out using specific field data and a spoofing injection test environment. The results show that the proposed solution can achieve a higher estimation performance over related modeling methods, which demonstrates the great potential in enhancing the perception capability under the GNSS spoofing attack situation in GNSS-based train positioning.