A False Data Injection Attack Detection Approach Using Convolutional Neural Networks in Unmanned Aerial Systems

Abstract

With the growing use of Unmanned Aerial Vehicles (UAVs) in military and civilian applications, cyber-attacks are increasing significantly. Therefore, detection of attacks becomes indispensable for such systems. In this paper, we focus on the detection of False Data Injection (FDI) attacks in Unmanned Aerial Systems (UASs). Considered to be the most performed attack, an attacker injects fake data into the system in order to disrupt the final decision. To combat this threat, our proposal is built on image analysis and classification. First, we resize the received image in order to adapt it to feed the classifier using the Nearest Neighbor Interpolation (NNI). Second, we train, validate, and test a Convolutional Neural Network (CNN) to perform the image classification. Finally, we compare each classification result classes to a neighborhood using Euclidean distance. Numerical results on the VisDrone dataset demonstrate the efficiency of our proposal under a set of metrics.