Eavesdropping Attack Detection in UAVs using Ensemble Learning

Abstract

The use of Unmanned Aerial Vehicles (UAVs) is proliferated and is prone to cyber attacks. Eavesdropping attack is an active threat to the security of an UAV as attackers intercept the communication medium over the wireless communication networks and get access to sensitive information. An active eavesdropper infiltrates the system and attacks the UAV during authentication. It involves the unauthorized interception of communication signals between the UAV and its control system. This type of intrusion can have severe consequences, including loss of control over the UAV, theft, espionage, and sabotage. To maintain the privacy and security of UAV communications and to protect sensitive information from unauthorized access, the detection of eavesdropping is of utmost importance. For the detection of eavesdropping attacks, we build an ensemble learning model with supervised machine learning algorithms (Logistic Regression, Decision Tree, Random Forest, k-Nearest Neighbours and Support Vector Machine) and unsupervised learning methods (One Class Support Vector Machine and K-Means Clustering). By combining the predictions of multiple algorithms, ensemble learning enhances the security and privacy of UAV communication. Additionally, by pooling together the strengths of different algorithms, ensemble learning improves the overall robustness and resilience of the UAV communication system and is a beneficial approach for the detection of eavesdropping attack packets. To train our proposed model we use the Kitsune Network Attack dataset. From the results, it is observed that our ensemble learning approach is a valid stratagem and can be used to detect eavesdropping attacks on UAV.