Deep Sequence-to-Sequence Models for GNSS Spoofing Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915571174473728 |
|---|---|
| author | Zelinka, Jan Kost, Oliver Hrúz, Marek |
| author_facet | Zelinka, Jan Kost, Oliver Hrúz, Marek |
| contents | 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%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_19890 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Deep Sequence-to-Sequence Models for GNSS Spoofing Detection Zelinka, Jan Kost, Oliver Hrúz, Marek Cryptography and Security Machine Learning 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%. |
| title | Deep Sequence-to-Sequence Models for GNSS Spoofing Detection |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2510.19890 |