$\recap$ : Protecting Cooperative Adaptive Cruise Control Against Multi-Channel Perception Adversary

Cooperative Adaptive Cruise Control (CACC) is a fundamental connected vehicle application. In CACC, a vehicle coordinates its longitudinal movements to safely and efficiently follow the vehicle in front. The follower vehicle relies on a combination of sensory and communication inputs to identify the position, velocity, and acceleration of the preceding vehicle. Malicious subversion of these inputs can cause catastrophic accidents, string instability, and disruption in the transportation infrastructure. In this paper, we develop a security system,
$\recap$
, to provide real-time resiliency in CACC against adversarial subversion of both sensory and communication inputs.
$\recap$
makes use of a combination of techniques based on kinematics and machine learning to detect anomalous inputs, narrow down the source of subversion, and perform mitigation. We provide extensive simulations to demonstrate the effectiveness of
$\recap$
against a diverse spectrum of attacks under complex, multi-channel adversaries.