智能汽车的入侵检测系统安全研究

On the security of the intrusion detection system in smart vehicles

车联网应用是典型的关联系统应用,智能汽车不仅其内部组件之间有网络连接,而且通过道路单元和其他汽车与外部世界也发生着关系。在很多场景下,内部网络和外部网络的数据包会经过相同的硬件,仅仅通过软件定义的规则进行隔离,任何错误的配置都可能将汽车内部组件暴露给黑客,从而导致灾难性的后果。提出巡航控制场景下的两种隐蔽攻击方法,研究智能汽车的自适应巡航控制系统在隐蔽攻击下的安全性,并提出一种新颖的入侵检测和补偿机制来发现和处理这些攻击。入侵检测系统引擎使用神经网络识别器去动态估算系统输出,并与巡航系统的输出进行比对。如果监测到任何异常,内置的补偿控制器将会激活并接管系统控制权。大量的模拟仿真实验表明,新方案反应快速且有效。

As the Internet of Vehicles matures and becomes widely used,the security challenges that come with it are increasing.Vehicular networks and smart cars are classic applications of inter-connected systems.Smart vehicles not only have networks connecting their internal components,but also are connected to the outside world by roadside units and other vehicles.In some cases,the internal and external network packets pass through the same hardware and are merely isolated by software defined rules.Any misconfiguration opens a window for the hackers to intrude into vehicles’internal components,which can lead to disastrous outcomes.In this paper,we define two covert attacks in the context of cruise control and propose a novel intrusion detection and compensation method to disclose and respond to such attacks.First,we employ a neural network identifier in the IDS engine to estimate the system output dynamically and compare it with the ACC output.If any anomaly is detected,an embedded compensation controller kicks in and takes over the control of the system.We conducted extensive experiments in the MATLAB to evaluate the effectiveness of the proposed scheme in a simulated environment.