| Title | A Convolutional Encoder Network for Intrusion Detection in Controller Area Networks |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Zhang, Xing, Cui, Xiaotong, Cheng, Kefei, Zhang, Liang |
| Conference Name | 2020 16th International Conference on Computational Intelligence and Security (CIS) |
| Keywords | CNN, Computational modeling, controller area network, controller area network security, Cyber-physical systems, data mining, Data processing, false negative rate, feature extraction, IDS, Internet of Things, network intrusion detection, Network Security Architecture, pubcrawl, Resiliency, security, Training |
| Abstract | Integrated with various electronic control units (ECUs), vehicles are becoming more intelligent with the assistance of essential connections. However, the interaction with the outside world raises great concerns on cyber-attacks. As a main standard for in-vehicle network, Controller Area Network (CAN) does not have any built-in security mechanisms to guarantee a secure communication. This increases risks of denial of service, remote control attacks by an attacker, posing serious threats to underlying vehicles, property and human lives. As a result, it is urgent to develop an effective in-vehicle network intrusion detection system (IDS) for better security. In this paper, we propose a Feature-based Sliding Window (FSW) to extract the feature of CAN Data Field and CAN IDs. Then we construct a convolutional encoder network (CEN) to detect network intrusion of CAN networks. The proposed FSW-CEN method is evaluated on real-world datasets. The experimental results show that compared to traditional data processing methods and convolutional neural networks, our method is able to detect attacks with a higher accuracy in terms of detection accuracy and false negative rate. |
| DOI | 10.1109/CIS52066.2020.00084 |
| Citation Key | zhang_convolutional_2020 |
A Convolutional Encoder Network for Intrusion Detection in Controller Area Networks