Accelerating In-vehicle Network Intrusion Detection System using Binarized Neural Network
2022-01-0186
03/29/2022
- Event
- Content
- Modern vehicles are utilizing more software modules and interfaces while new risks and attacks are emerging and threatening the security of vehicles. Researchers demonstrate that in-vehicle networks have become a target of vehicle attackers. Controller Area Network (CAN), the de facto standard for in-vehicle networks, has insufficient security features and thus is inherently vulnerable to various attacks. Intrusion detection systems (IDSs) based on advanced deep learning methods, such as Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN), have been proposed to protect CAN bus from attacks. However, those models generally introduce high latency and require considerable computing resources. To accelerate intrusion detection and also reduce both latency and model size, we propose a new IDS system based on Binarized Neural Network (BNN). As BNN uses binary values for activations and weights rather than full precision values, it usually results in faster computation and smaller model size than full precision models. We design our BNN model that is suitable for the CAN traffic data to achieve satisfying detection rates while accelerating the detection process. To detect intrusions, our IDS exploits sequential features of the CAN traffic instead of individual messages. Furthermore, unlike other deep learning-based IDSs, the detection process of our IDS can be further accelerated by leveraging Field-Programmable Grid Arrays (FPGAs) since BNN cuts down the hardware consumption. We evaluate the proposed IDS over four different real vehicle datasets. Our experimental results show that the proposed BNN-based IDS reduces the detection latency and model size while maintaining acceptable detection rates compared to full precision models. We also conduct experiments on different platforms. The results demonstrate that the detection latency can be further reduced on an FPGA with low power consumption in comparison with an embedded CPU.
- Citation
- Zhang, L., Yan, X., and Ma, D., "Accelerating In-vehicle Network Intrusion Detection System using Binarized Neural Network," SAE Technical Paper 2022-01-0186, 2022, .