A Deep-Learning-Based GPS Signal Spoofing Detection Method for Small UAVs

被引:12
|
作者
Sun, Yichen [1 ,2 ,3 ]
Yu, Mingxin [2 ]
Wang, Luyang [2 ]
Li, Tianfang [2 ]
Dong, Mingli [2 ,3 ]
机构
[1] Beijing Univ Technol, Fac Mat & Mfg, Beijing 100124, Peoples R China
[2] Beijing Informat Sci & Technol Univ, Minist Educ Optoelect Measurement Technol & Instru, Key Lab, Beijing 100016, Peoples R China
[3] Guangzhou Nansha Intelligent Photon Sensing Res In, Guangzhou 511462, Peoples R China
关键词
global positioning system (GPS); spoofing; convolutional neural network (CNN); long short-term memory (LSTM); support vector machines-synthetic minority oversampling technique (SVM-SMOTE); principal component analysis (PCA); ATTACK;
D O I
10.3390/drones7060370
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
The navigation of small unmanned aerial vehicles (UAVs) mainly depends on global positioning systems (GPSs). However, GPSs are vulnerable to attack by spoofing, which causes the UAVs to lose their positioning ability. To address this issue, we propose a deep learning method to detect the spoofing of GPS signals received by small UAVs. Firstly, we describe the GPS signal dataset acquisition and preprocessing methods; these include the hardware system of the UAV and the jammer used in the experiment, the time and weather conditions of the data collection, the use of Spearman correlation coefficients for preprocessing, and the use of SVM-SMOTE to solve the spoofing data imbalance. Next, we introduce a PCA-CNN-LSTM model. We used principal component analysis (PCA) of the model to extract feature information related to spoofing from the GPS signal dataset. The convolutional neural network (CNN) in the model was used to extract local features in the GPS signal dataset, and long short-term memory (LSTM) was used as a posterior module of the CNN for further processing and modeling. To minimize randomness and chance in the simulation experiments, we used the 10-fold cross-validation method to train and evaluate the computational performance of our spoofing machine learning model. We conducted a series of experiments in a numerical simulation environment and evaluated the proposed model against the most advanced traditional machine learning and deep learning models. The results and analysis show that the PCA-CNN-LSTM neural network model achieved the highest accuracy (0.9949). This paper provides a theoretical basis and technical support for spoofing detection for small-UAV GPS signals.
引用
收藏
页数:24
相关论文
共 50 条
  • [1] A Vision-Based GPS-Spoofing Detection Method for Small UAVs
    Qiao, Yinrong
    Zhang, Yuxing
    Du, Xiao
    2017 13TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND SECURITY (CIS), 2017, : 312 - 316
  • [2] Deep-Ensemble-Learning-Based GPS Spoofing Detection for Cellular-Connected UAVs
    Dang, Yongchao
    Benzaid, Chafika
    Yang, Bin
    Taleb, Tarik
    Shen, Yulong
    IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (24) : 25068 - 25085
  • [3] Deep Learning Detection of GPS Spoofing
    Jullian, Olivia
    Otero, Beatriz
    Stojilovic, Mirjana
    Jose Costa, Juan
    Verdu, Javier
    Alejandro Pajuelo, Manuel
    MACHINE LEARNING, OPTIMIZATION, AND DATA SCIENCE (LOD 2021), PT I, 2022, 13163 : 527 - 540
  • [4] Detection of GPS Spoofing Attacks in UAVs Based on Adversarial Machine Learning Model
    Alhoraibi, Lamia
    Alghazzawi, Daniyal
    Alhebshi, Reemah
    SENSORS, 2024, 24 (18)
  • [5] Transfer Learning based GPS Spoofing Detection for Cellular-Connected UAVs
    Dang, Yongchao
    Benzaid, Chafika
    Taleb, Tarik
    Bin Yang
    Shen, Yulong
    2022 INTERNATIONAL WIRELESS COMMUNICATIONS AND MOBILE COMPUTING, IWCMC, 2022, : 629 - 634
  • [6] Adversarial Examples on Deep-Learning-Based ADS-B Spoofing Detection
    Shang, Fute
    Wang, Buhong
    Li, Tengyao
    Tian, Jiwei
    Cao, Kunrui
    Guo, Rongxiao
    IEEE WIRELESS COMMUNICATIONS LETTERS, 2020, 9 (10) : 1734 - 1737
  • [7] GPS Spoofing Detection Method for Small UAVs Using 1D Convolution Neural Network
    Sung, Young-Hwa
    Park, Soo-Jae
    Kim, Dong-Yeon
    Kim, Sungho
    SENSORS, 2022, 22 (23)
  • [8] Deep-Learning-Based Signal Detection for Banded Linear Systems
    Fan, Congmin
    Yuan, Xiaojun
    Zhang, Ying-Jun Angela
    2018 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2018,
  • [9] A GPS Spoofing Signal Detection Method Based on Low Frequency Power Spectrum
    Li, Guangjie
    Peng, Yue
    Ma, Jiajun
    Wu, Dandan
    Zhan, Qiang
    Chang, Yuanpei
    Xue, Yin
    Zhang, Yu
    Zuo, Jiancun
    WIRELESS PERSONAL COMMUNICATIONS, 2024, 139 (03) : 1783 - 1795
  • [10] CTDNN-Spoof: compact tiny deep learning architecture for detection and multi-label classification of GPS spoofing attacks in small UAVs
    Almadhor, Ahmad
    Baili, Jamel
    Alsubai, Shtwai
    Al Hejaili, Abdullah
    Kulhanek, Rastislav
    Abbas, Sidra
    SCIENTIFIC REPORTS, 2025, 15 (01):