Search for: All records

Vehicles can utilize their sensors or receive messages from other vehicles to acquire information about the surrounding environments. However, the information may be inaccurate, faulty, or maliciously compromised due to sensor failures, communication faults, or security attacks. The goal of this work is to detect if a lane-changing decision and the sensed or received information are anomalous. We develop three anomaly detection approaches based on deep learning: a classifier approach, a predictor approach, and a hybrid approach combining the classifier and the predictor. All of them do not need anomalous data nor lateral features so that they can generally consider lane-changing decisions before the vehicles start moving along the lateral axis. They achieve at least 82% and up to 93% F1 scores against anomaly on data from Simulation of Urban MObility (SUMO) and HighD. We also examine system properties and verify that the detected anomaly includes more dangerous scenarios. 

Connected Autonomous Vehicular (CAV) platoon refers to a group of vehicles that coordinate their movements and operate as a single unit. The vehicle at the head acts as the leader of the platoon and determines the course of the vehicles following it. The follower vehicles utilize Vehicle-to-Vehicle (V2V) communication and automated driving support systems to automatically maintain a small fixed distance between each other. Reliance on V2V communication exposes platoons to several possible malicious attacks which can compromise the safety, stability, and efficiency of the vehicles. We present a novel distributed resiliency architecture, RePLACe for CAV platoon vehicles to defend against adversaries corrupting V2V communication reporting preceding vehicle position. RePLACe is unique in that it can provide real-time defense against a spectrum of communication attacks. RePLACe provides systematic augmentation of a platoon controller architecture with real-time detection and mitigation functionality using machine learning. Unlike computationally intensive cryptographic solutions RePLACe accounts for the limited computation capabilities provided by automotive platforms as well as the real-time requirements of the application. Furthermore, unlike control-theoretic approaches, the same framework works against the broad spectrum of attacks. We also develop a systematic approach for evaluation of resiliency of CAV applications against V2V attacks. We perform extensive experimental evaluation to demonstrate the efficacy of RePLACe. 

Autonomous vehicle-following systems, including Adaptive Cruise Control (ACC) and Cooperative Adaptive Cruise Control (CACC), improve safety, efficiency, and string stability for a vehicle (the ego vehicle) following its leading vehicle. The ego vehicle senses or receives information, such as the position, velocity, acceleration, or even intention, of the leading vehicle and controls its own behavior. However, it has been shown that sensors and wireless channels are vulnerable to security attacks, and attackers can modify data sensed from sensors or received from other vehicles. To address this problem, in this paper, we design three types of stealthy attacks on ACC or CACC inputs, where the stealthy attacks can deceive a rule-based detection approach and impede system properties (collision-freeness and vehicle-following distance). We then develop two deep-learning models, a predictor-based model and an encoder-decoder-based model to detect the attacks, where the two models do not need attacker models for training. The experimental results demonstrate the respective strengths of different models and lead to a methodology for the design of learning-based intrusion detection approaches.