Scholarlink

The Controller Area Network (CAN) is widely used in the automotive industry for its ability to create inexpensive and fast networks. However, it lacks an authentication scheme, making vehicles vulnerable to spoofing attacks. Evidence shows that attackers can remotely control vehicles, posing serious risks to passengers and pedestrians. Several strategies have been proposed to ensure CAN data integrity by identifying senders based on physical layer characteristics, but high computational costs limit their practical use. This paper presents a framework to efficiently identify CAN bus system senders by fingerprinting them. By modeling the CAN sender identification problem as an image classification task, the need for expensive handcrafted feature engineering is eliminated, improving accuracy using deep neural networks. Experimental results show the proposed methodology achieves a maximum identification accuracy of 98.34%, surpassing the state-of-the-art method’s 97.13%. The approach also significantly reduces computational costs, cutting data processing time by a factor of 27, making it feasible for real-time application in vehicles. When tested on an actual vehicle, the proposed methodology achieved a no-attack detection rate of 97.78% and an attack detection rate of 100%, resulting in a combined accuracy of 98.89%. These results highlight the framework’s potential to enhance vehicle cybersecurity by reliably and efficiently identifying CAN bus senders.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An Efficient and Applicable Physical Fingerprinting Framework for the Controller Area Network Utilizing Deep Learning Algorithm Trained on Recurrence Plots

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Rafi Ud Daula Refat,
  • Alireza Mohammadi,
  • Hafiz Malik

摘要

The Controller Area Network (CAN) is widely used in the automotive industry for its ability to create inexpensive and fast networks. However, it lacks an authentication scheme, making vehicles vulnerable to spoofing attacks. Evidence shows that attackers can remotely control vehicles, posing serious risks to passengers and pedestrians. Several strategies have been proposed to ensure CAN data integrity by identifying senders based on physical layer characteristics, but high computational costs limit their practical use. This paper presents a framework to efficiently identify CAN bus system senders by fingerprinting them. By modeling the CAN sender identification problem as an image classification task, the need for expensive handcrafted feature engineering is eliminated, improving accuracy using deep neural networks. Experimental results show the proposed methodology achieves a maximum identification accuracy of 98.34%, surpassing the state-of-the-art method’s 97.13%. The approach also significantly reduces computational costs, cutting data processing time by a factor of 27, making it feasible for real-time application in vehicles. When tested on an actual vehicle, the proposed methodology achieved a no-attack detection rate of 97.78% and an attack detection rate of 100%, resulting in a combined accuracy of 98.89%. These results highlight the framework’s potential to enhance vehicle cybersecurity by reliably and efficiently identifying CAN bus senders.