Deep Ensemble Learning based GPS Spoofing Detection for Cellular-Connected UAVs

Yongchao Dang, Chafika Benzaid, Bin Yang, Tarik Taleb, Yulong Shen

    Research output: Contribution to journalArticleScientificpeer-review

    46 Citations (Scopus)
    82 Downloads (Pure)

    Abstract

    Unmanned Aerial Vehicles (UAVs) are an emerging technology in the 5G and beyond systems with the promise of assisting cellular communications and supporting IoT deployment in remote and density areas. Safe and secure navigation is essential for UAV remote and autonomous deployment. Indeed, the open-source simulator can use commercial software-defined radio tools to generate fake GPS signals and spoof the UAV GPS receiver to calculate wrong locations, deviating from the planned trajectory. Fortunately, the existing mobile positioning system can provide additional navigation for cellular-connected UAVs and verify the UAV GPS locations for spoofing detection, but it needs at least three base stations at the same time. In this paper, we propose a novel deep ensemble learning-based, mobile network-assisted UAV monitoring and tracking system for cellular-connected UAV spoofing detection. The proposed method uses path losses between base stations and UAVs communication to indicate the UAV trajectory deviation caused by GPS spoofing. To increase the detection accuracy, three statistics methods are adopted to remove environmental impacts on path losses. In addition, deep ensemble learning methods are deployed on the edge cloud servers and use the multi-layer perceptron (MLP) neural networks to analyze path losses statistical features for making a final decision, which has no additional requirements and energy consumption on UAVs. The experimental results show the effectiveness of our method in detecting GPS spoofing, achieving above 97% accuracy rate under two BSs, while it can still achieve at least 83% accuracy under only one BS.

    Original languageEnglish
    Pages (from-to)25068-25085
    Number of pages18
    JournalIEEE Internet of Things Journal
    Volume9
    Issue number24
    Early online date1 Aug 2022
    DOIs
    Publication statusPublished - 15 Dec 2022
    MoE publication typeA1 Journal article-refereed

    Keywords

    • Autonomous aerial vehicles
    • Base stations
    • Deep ensemble learning
    • Encryption
    • Global Positioning System
    • GPS spoofing
    • Multi-Layer Perceptron (MLP)
    • Navigation
    • Path loss
    • Receivers
    • Servers
    • UAV

    Fingerprint

    Dive into the research topics of 'Deep Ensemble Learning based GPS Spoofing Detection for Cellular-Connected UAVs'. Together they form a unique fingerprint.

    Cite this