Comparative Study of Machine Learning Techniques for Detecting GPS Spoofing Attacks on Mission Critical Military IoT Devices

In military Internet of Things (IoT) devices, which rely on accurate GPS information for navigation, communication, and other critical functions, GPS spoofing has become a growing threat. A method based on artificial intelligence has been proposed for detecting GPS spoofing attacks on military IoT devices. Using Python programming, we built a synthetic GPS dataset to address this issue. We evaluated the selected machine learning models on a synthetic dataset of GPS spoofing attacks. The results of our work indicate that LightXGBoost outperforms traditional algorithms, such as SVM and KNN, in terms of accuracy, precision, and F1 Score. XGBoost, on the other hand, provides good results in terms of detection time and memory consumption. Additionally, we have demonstrated that synthetic datasets can be useful for detecting spoofing attacks on IoT devices using XGBoost and LightXGBoost.