Detection of False Data Injection Attack in Connected and Automated Vehicles via Cloud-Based Sandboxing
Detection of False Data Injection Attack in Connected and Automated Vehicles via Cloud-Based Sandboxing
复制标题
通过基于云的沙盒检测联网和自动化车辆中的虚假数据注入攻击
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
G. Comert
中科院分区：
文献类型：
--
作者：
Chunheng Zhao;J. S. Gill;P. Pisu;G. Comert
近年来，车联网通信（V2X）在队列行驶和防撞等应用中的发展稳步增长。V2X为车辆提供有关交通拥堵和路线的远程信息，以及允许协作自适应巡航控制、自动碰撞警告等的短程和中程信息。尽管在几个方面有潜在的好处，但这种相互依赖性从安全性和可靠性的角度来看，由于旨在影响车辆行为的网络攻击的可能性，带来了一系列具体的挑战。本文提出了一种基于云的方法，沙箱框架，以检测连接和自动车辆（CAV）上的虚假数据注入攻击。沙箱的概念来自于计算机安全，它被采用在控制框架中，作为一种隔离和评估影响飞行器控制系统的CAV交换的数据的方法。数值实验表明，该方法的有效性，使用微观交通模拟。仿真结果表明，该方法能够检测V2X通信中存在的虚假数据注入攻击，并在0.2 s内实时识别攻击者。
In recent years, developments in vehicle-to-everything communication (V2X) have steadily increased in applications such as platooning and collision avoidance. V2X provides vehicles with long-range information regarding traffic congestion and routing, but also short and mid-range information allowing cooperative adaptive cruise control, automatic collision warnings, and others. Despite being potentially beneficial in several aspects, such interdependence poses a set of specific challenges from safety and reliability standpoint due to the possibility of cyber-attacks aimed at influencing the behavior of the vehicles. In this paper, a Cloud-based approach, a sandboxing framework is presented to detect the false data injection attack on connected and automated vehicles (CAVs). The sandboxing concept comes from computer security and it is adopted in a control framework as a way to isolate and evaluate the data exchanged by the CAVs affecting the vehicle control system. Numerical experiments are conducted to show the effectiveness of the approach using microscopic traffic simulation. Simulation results show that our proposed methodology is able to detect the false data injection attack existing in the V2X communication and identify the attacker in real-time less than 0.2 s.