2026-04-17T02:54:16Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/3630002026-01-23T05:22:14Zcom_2072_1033col_2072_452950

Deep learning detection of GPS spoofing Jullian Parra, Olivia Otero Calviño, Beatriz Stojilovic, Mirjana Costa Prats, Juan José Verdú Mulà, Javier Pajuelo González, Manuel Alejandro Universitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors Universitat Politècnica de Catalunya. VIRTUOS - Virtualisation and Operating Systems Àrees temàtiques de la UPC::Informàtica::Seguretat informàtica Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Radiocomunicació i exploració electromagnètica::Satèl·lits i ràdioenllaços Computer security Drone aircraft Deep learning Global Positioning System Intrusion detection model Unmanned aerial vehicles Spoofing Global navigation satellite system Seguretat informàtica Avions no tripulats Aprenentatge profund Sistema de posicionament global Unmanned aerial vehicles (UAVs) are widely deployed in air navigation, where numerous applications use them for safety-of-life and positioning, navigation, and timing tasks. Consequently, GPS spoofing attacks are more and more frequent. The aim of this work is to enhance GPS systems of UAVs, by providing the ability of detecting and preventing spoofing attacks. The proposed solution is based on a multilayer perceptron neural network, which processes the flight parameters and the GPS signals to generate alarms signalling GPS spoofing attacks. The obtained accuracy lies between 83.23% for TEXBAT dataset and 99.93% for MAVLINK dataset. This work was supported in part by the Catalan Government, through the program 2017-SGR-962 and the RIS3CAT DRAC project 001-P-001723, and by the EPFL, Switzerland. Peer Reviewed Postprint (author's final draft) 2022 Conference report Jullian, O. [et al.]. Deep learning detection of GPS spoofing. A: International Conference on Machine Learning, Optimization, and Data Science. "Machine Learning, Optimization, and Data Science, 7th International Conference, LOD 2021: Grasmere, UK, October 4-8, 2021: revised selected papers, part I". Springer Nature, 2022, p. 527-540. ISBN 978-3-030-95467-3. DOI 10.1007/978-3-030-95467-3_38. 978-3-030-95467-3 https://hdl.handle.net/2117/363000 10.1007/978-3-030-95467-3_38 eng https://link.springer.com/chapter/10.1007/978-3-030-95467-3_38 info:eu-repo/grantAgreement/GENCAT/RIS3CAT/IU16-011643 VIRTUOS P6 Open Access 14 p. application/pdf Springer Nature