GPS Spoofing Detection Method for Small UAVs Using 1D Convolution Neural Network is a work by Young-Hwa Sung, Soo-Jae Park, Dong-Yeon Kim, and Sungho Kim.
Small unmanned aerial vehicles (UAVs), like quadcopters, heavily rely on the global positioning system (GPS) for navigation. However, they are susceptible to GPS spoofing attacks, wherein malicious actors attempt to manipulate a UAV’s GPS receiver by transmitting falsified signals. Commercial GPS simulators can deceive GPS-guided drones, causing them to deviate from their intended paths. To ensure the safe operation of UAVs, it is crucial to employ anti-spoofing techniques. While various methods have been developed to detect GPS spoofing, many require additional hardware, which may not be suitable for small UAVs with limited resources.
This study introduces a lightweight and power-efficient anti-spoofing approach based on deep learning, specifically employing a 1D convolutional neural network. This method enables real-time detection on mobile platforms and can be further improved by expanding training data and adjusting the network architecture. Evaluation of a drone’s embedded board considered power consumption and inference time. The proposed method exhibited superior precision, recall, and F-1 score performance compared to support vector machines. Additionally, flight tests demonstrated the algorithm’s effectiveness in detecting GPS spoofing attacks.
Publication Date– December 2022
GPS Spoofing Detection Method for Small UAVs Using 1D Convolution Neural Network contains the following major sections:
- Related Works
- GPS Spoofing Detection Method Based on Deep Learning
All articles published by MDPI are immediately available worldwide under an open-access license. No special permission is required to reuse all or part of the article published by MDPI, including figures and tables. Any part of the article may be reused without the consent for articles published under an open-access Creative Common CC BY license, provided the original article is clearly cited. For more information, please refer to https://www.mdpi.com/openaccess.
C-UAS Hub does not own this content and provides a link for users at the bottom of the page to access it in its original location. This allows the author(s) to track important article metrics related to their work. All credit goes to its rightful owner.
Authors- Young-Hwa Sung, Soo-Jae Park, Dong-Yeon Kim, and Sungho Kim.
Post Image- GPS spoofing signal simulation environment. (Image Credit: Authors)