主办:陕西省汽车工程学会
ISSN 1671-7988  CN 61-1394/TH
创刊:1976年

汽车实用技术 ›› 2025, Vol. 50 ›› Issue (4): 34-40,78.DOI: 10.16638/j.cnki.1671-7988.2025.004.006

• 智能网联汽车 • 上一篇    

基于两步算法的智能网联汽车入侵检测系统

简永沛 1,武智 1,熊迪 2,贾先锋 1   

  1. 1.中汽智联技术有限公司;2.中汽数据(天津)有限公司
  • 发布日期:2025-02-25
  • 通讯作者: 简永沛
  • 作者简介:简永沛(1997-),男,硕士,助理工程师,研究方向为车联网,E-mail:2509552958@qq.com

Intrusion Detection System in Intelligent Connected Vehicle Based on Two-step Algorithm

JIAN Yongpei1 , WU Zhi1 , XIONG Di2 , JIA Xianfeng1   

  1. 1.CATARC Intelligent and Connected Technology Company Limited; 2.Automotive Data of China (Tianjin) Company Limited
  • Published:2025-02-25
  • Contact: JIAN Yongpei

摘要: 智能网联汽车是物联网中不可分割的对象,在保障车辆的安全性和可靠性方面,汽车 行业正面临着巨大的挑战。在这种情况下,智能网联汽车供应商致力于提供安全的系统,保 障用户的行驶安全,使其免受可能的网络攻击。文章提出了一种适用于智能网联汽车的嵌入 式入侵检测系统,采用两步算法对可能的网络攻击进行检测。为了评估该方法的有效性,进 行了实验测试,计算了经典的准确性评估参数,并与文献中的网络攻击数据集进行了比较。 结果表明,该方法对于常见的网络攻击(DoS、模糊、冒充)具有更加优越的检测性能。在 Free State 攻击下测试该方法时,性能有所降低。

关键词: 入侵检测系统;网络安全;智能网联汽车;贝叶斯网络

Abstract: The intelligent connected vehicle is an inseparable object in the internet of things. In terms of ensuring the safety and reliability of vehicles, the automotive industry is facing great challenges. In this context, intelligent connected vehicle providers are committed to providing secure systems that keep users safe from possible cyber attacks. This paper presents an embedded intrusion detection system for intelligent networked vehicles, which uses a two-step algorithm to detect possible network attacks. In order to evaluate the effectiveness of this method, experimental tests are carried out, classical accuracy evaluation parameters are calculated, and comparison is made with network attack data sets in the literature. The results show that this method has better detection performance for common network attacks (DoS, fuzzy, impersonation). When testing this method under Free State attacks, performance degrades.

Key words: intrusion detection system; network security; intelligent connected vehicles; Bayesian network