Deep Learning for GPS Spoofing Detection in Cellular-Enabled UAV Systems

Yongchao Dang; Chafika Benzaid; Bin Yang; Tarik Taleb

doi:10.1109/NaNA53684.2021.00093

Deep Learning for GPS Spoofing Detection in Cellular-Enabled UAV Systems

Yongchao Dang
, Chafika Benzaid
, Bin Yang
, Tarik Taleb

University of Oulu

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

23 Citations (Scopus)

Abstract

Cellular-based Unmanned Aerial Vehicle (UAV) systems are a promising paradigm to provide reliable and fast Beyond Visual Line of Sight (BVLoS) communication services for UAV operations. However, such systems are facing a serious GPS spoofing threat for UAV's position. To enable safe and secure UAV navigation BVLoS, this paper proposes a cellular network assisted UAV position monitoring and anti-GPS spoofing system, where deep learning approach is used to live detect spoofed GPS positions. Specifically, the proposed system introduces a MultiLayer Perceptron (MLP) model which is trained on the statistical properties of path loss measurements collected from nearby base stations to decide the authenticity of the GPS position. Experiment results indicate the accuracy rate of detecting GPS spoofing under our proposed approach is more than 93% with three base stations and it can also reach 80% with only one base station.

Original language	English
Title of host publication	Proceedings - 2021 International Conference on Networking and Network Applications, NaNA 2021
Publisher	IEEE
Pages	501-506
Number of pages	6
ISBN (Electronic)	978-1-6654-4158-2
DOIs	https://doi.org/10.1109/NaNA53684.2021.00093
Publication status	Published - 10 Dec 2021
MoE publication type	A4 Conference publication
Event	International Conference on Networking and Network Applications - Lijiang City, China Duration: 29 Oct 2021 → 1 Nov 2021 http://www.nana-conference.org/

Conference

Conference	International Conference on Networking and Network Applications
Abbreviated title	NaNa
Country/Territory	China
City	Lijiang City
Period	29/10/2021 → 01/11/2021
Internet address	http://www.nana-conference.org/

Keywords

Deep Learning
GPS spoofing
MLP
Path Loss
UAV

Access to Document

10.1109/NaNA53684.2021.00093

https://arxiv.org/abs/2201.00568

Cite this

@inproceedings{b71b954e4e9c40d88b29e34f96d2c195,

title = "Deep Learning for GPS Spoofing Detection in Cellular-Enabled UAV Systems",

abstract = "Cellular-based Unmanned Aerial Vehicle (UAV) systems are a promising paradigm to provide reliable and fast Beyond Visual Line of Sight (BVLoS) communication services for UAV operations. However, such systems are facing a serious GPS spoofing threat for UAV's position. To enable safe and secure UAV navigation BVLoS, this paper proposes a cellular network assisted UAV position monitoring and anti-GPS spoofing system, where deep learning approach is used to live detect spoofed GPS positions. Specifically, the proposed system introduces a MultiLayer Perceptron (MLP) model which is trained on the statistical properties of path loss measurements collected from nearby base stations to decide the authenticity of the GPS position. Experiment results indicate the accuracy rate of detecting GPS spoofing under our proposed approach is more than 93\% with three base stations and it can also reach 80\% with only one base station. ",

keywords = "Deep Learning, GPS spoofing, MLP, Path Loss, UAV",

author = "Yongchao Dang and Chafika Benzaid and Bin Yang and Tarik Taleb",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE. | openaire: EC/H2020/871808/EU//INSPIRE-5Gplus | openaire: EC/H2020/857031/EU//5G!Drones; International Conference on Networking and Network Applications, NaNa ; Conference date: 29-10-2021 Through 01-11-2021",

year = "2021",

month = dec,

day = "10",

doi = "10.1109/NaNA53684.2021.00093",

language = "English",

pages = "501--506",

booktitle = "Proceedings - 2021 International Conference on Networking and Network Applications, NaNA 2021",

publisher = "IEEE",

address = "United States",

url = "http://www.nana-conference.org/",

}

Dang, Y, Benzaid, C, Yang, B & Taleb, T 2021, Deep Learning for GPS Spoofing Detection in Cellular-Enabled UAV Systems. in Proceedings - 2021 International Conference on Networking and Network Applications, NaNA 2021. IEEE, pp. 501-506, International Conference on Networking and Network Applications, Lijiang City, China, 29/10/2021. https://doi.org/10.1109/NaNA53684.2021.00093

Deep Learning for GPS Spoofing Detection in Cellular-Enabled UAV Systems. / Dang, Yongchao; Benzaid, Chafika; Yang, Bin et al.
Proceedings - 2021 International Conference on Networking and Network Applications, NaNA 2021. IEEE, 2021. p. 501-506.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Deep Learning for GPS Spoofing Detection in Cellular-Enabled UAV Systems

AU - Dang, Yongchao

AU - Benzaid, Chafika

AU - Yang, Bin

AU - Taleb, Tarik

PY - 2021/12/10

Y1 - 2021/12/10

N2 - Cellular-based Unmanned Aerial Vehicle (UAV) systems are a promising paradigm to provide reliable and fast Beyond Visual Line of Sight (BVLoS) communication services for UAV operations. However, such systems are facing a serious GPS spoofing threat for UAV's position. To enable safe and secure UAV navigation BVLoS, this paper proposes a cellular network assisted UAV position monitoring and anti-GPS spoofing system, where deep learning approach is used to live detect spoofed GPS positions. Specifically, the proposed system introduces a MultiLayer Perceptron (MLP) model which is trained on the statistical properties of path loss measurements collected from nearby base stations to decide the authenticity of the GPS position. Experiment results indicate the accuracy rate of detecting GPS spoofing under our proposed approach is more than 93% with three base stations and it can also reach 80% with only one base station.

AB - Cellular-based Unmanned Aerial Vehicle (UAV) systems are a promising paradigm to provide reliable and fast Beyond Visual Line of Sight (BVLoS) communication services for UAV operations. However, such systems are facing a serious GPS spoofing threat for UAV's position. To enable safe and secure UAV navigation BVLoS, this paper proposes a cellular network assisted UAV position monitoring and anti-GPS spoofing system, where deep learning approach is used to live detect spoofed GPS positions. Specifically, the proposed system introduces a MultiLayer Perceptron (MLP) model which is trained on the statistical properties of path loss measurements collected from nearby base stations to decide the authenticity of the GPS position. Experiment results indicate the accuracy rate of detecting GPS spoofing under our proposed approach is more than 93% with three base stations and it can also reach 80% with only one base station.

KW - Deep Learning

KW - GPS spoofing

KW - MLP

KW - Path Loss

KW - UAV

UR - https://www.scopus.com/pages/publications/85123977867

U2 - 10.1109/NaNA53684.2021.00093

DO - 10.1109/NaNA53684.2021.00093

M3 - Conference article in proceedings

AN - SCOPUS:85123977867

SP - 501

EP - 506

BT - Proceedings - 2021 International Conference on Networking and Network Applications, NaNA 2021

PB - IEEE

T2 - International Conference on Networking and Network Applications

Y2 - 29 October 2021 through 1 November 2021

ER -

Deep Learning for GPS Spoofing Detection in Cellular-Enabled UAV Systems

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

INSPIRE-5Gplus: INtelligent Security and PervasIve tRust for 5G and Beyond

5G!Drones: 5G for Drone-based Vertical Applications

Cite this

Deep Learning for GPS Spoofing Detection in Cellular-Enabled UAV Systems

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Projects

INSPIRE-5Gplus: INtelligent Security and PervasIve tRust for 5G and Beyond

5G!Drones: 5G for Drone-based Vertical Applications

Cite this