Abstract
In recent years, deep learning theories, such as Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN), have been applied as effective methods for intrusion detection in the vehicle CAN network. However, the existing RNNs realize detection by establishing independent models for each CAN ID, which are unable to learn the potential characteristics of different IDs well, and have relatively complicated model structure and high calculation time cost. CNNs can achieve rapid detection by learning the characteristics of normal and attack CAN ID sequences and exhibit good performance, but the current methods do not locate abnormal points in the sequence. To solve the above problems, this paper proposes an in-vehicle CAN network intrusion detection model based on Temporal Convolutional Network, which is called Temporal Convolutional Network-Based Intrusion Detection System (TCNIDS). In TCNIDS, the CAN ID is serialized into a natural language sequence and a word vector is constructed for each CAN ID through the word embedding coding method to reduce the data dimension. At the same time, TCNIDS uses the parameterized Relu method to improve the temporal convolutional network, which can better learn the potential features of the normal sequence. The TCNIDS model has a simple structure and realizes the point anomaly detection at the message level by predicting the future sequence of normal CAN data and setting the probability strategy. The experimental results show that the overall detection rate, false alarm rate, and accuracy rate of TCNIDS under fuzzy attack, spoofing attack, and DoS attack are higher than those of the traditional temporal convolutional network intrusion detection model.
Highlights
With the development of technologies such as the Internet of Vehicles, unmanned driving, and software-defined cars, modern cars are equipped with more and more advanced sensing devices and intelligent control systems [1], making cars more intelligent and providing people with a more comfortable driving service
Intrusion detection is an effective method to solve the problem of in-vehicle network security, of which the study of CAN data as a sequence is an important research field of current intrusion detection. e normal CAN ID sequence features are extracted through sequence learning, and when a nonexistent sequence appears in the network, the intrusion detection system detects it as an abnormality [6, 7]
Temporal Convolutional Network. e Temporal Convolutional Network-Based Intrusion Detection System (TCNIDS) model proposed in this paper extends on the general TCN model described in Ref. [10]. e TCN model has two main constraints. e output of the hidden layer in the middle of the model has the same length as the input, and the prediction at time t can only rely on the information before time t
Summary
With the development of technologies such as the Internet of Vehicles, unmanned driving, and software-defined cars, modern cars are equipped with more and more advanced sensing devices and intelligent control systems [1], making cars more intelligent and providing people with a more comfortable driving service. Song et al proposed an intrusion detection method based on a deep convolutional neural network [9], which learned normal and attack CAN ID sequence features through the convolutional network and achieved a higher detection rate while using the parallel processing capability of the convolutional network to reduce the time cost. It does not locate abnormal points and the abnormal detection of the message level is not realized.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
