Macroscopic-Model-Based Learning for Detection of Cyber-Attacks in UAV Swarms

This paper considers a class of cyber-attacks aimed at a swarm of unmanned aerial vehicles (UAVs). Our focus is on scenarios wherein an attacker may hack into a subset of vehicles in the swarm and subtly modify their flight parameters. These hacked vehicles (referred to as malicious vehicles) are subsequently able to modify the behavior of the overall swarm. The swarm comprising the mix of malicious and normal vehicles is modeled using a system of coupled partial differential equations (PDEs) in a two-dimensional Lighthill–Whitham–Richards model. We develop a methodology that combines Gaussian processes with wave propagation analysis of this two-species PDE model and use this method for detecting the presence of malicious vehicles in the swarm. Simulation results demonstrate that this methodology performs successful detection of the malicious vehicles and also identifies their mode of attack on the UAV swarm.