Multiple Attacks Intrusion Detection Framework for In-Vehicle Networks Based on Abnormal Data Features

An increasing number of security vulnerabilities have been found in the electronic control units (ECUs) and external communication interfaces of smart cars. Intrusion detection systems (IDS) have become the focus research as an initiative protection measure, yet the key issues are not well resolved, such as detection accuracy and computation overhead. According to vulnerability analysis and the different features of abnormal data under different attacks, an in-vehicle network experimental attack platform and an abnormal behavior characteristic library are built. Then, a low complexity learning algorithm is used to detect simple abnormal features. Next, a more complex detection method is proved to achieve accurate detection of abnormal data for abnormal behavior such as false data injecting and semantic tampering. Our research work makes it easy to understand intrusion detection systems for in-vehicle networks and benefits the implementation of security in the automotive industry.