Research on Machine Learning-based Network Security Situational Awareness Algorithm for UAV GNSS Signal Interference

With the widespread application of Unmanned Aerial Vehicle (UAV) in various fields, the problem of interference with their Global Navigation Satellite System (GNSS) signals is becoming increasingly serious, which puts forward higher requirements for network security situational awareness. This paper proposes an Integration Algorithm of Support Vector Machine and K-Nearest Neighbor (IASK) for network security situational awareness of UAV GNSS signal interference. This algorithm combines the advantages of Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) algorithms in binary classification problem scenarios, collects and pre-processes the GNSS signal, extract and classify the signal features, thereby realizing the detection and identification of interference signals. The experimental results show that compared to not using Machine Learning algorithms, IASK's detection and awareness of normal and interference signals in GNSS has increased accuracy from 83.31\% to 99.71\%, which proved IASK has high accuracy and real-time performance, and can significantly improve the security and reliability of the UAV GNSS signal interference network. This provides strong support for ensuring the normal operation and network security of UAV, and has important theoretical significance and practical application value.