FL-IoV：基于联邦学习的综合车联网入侵检测方法

蒋玉长; 蒋利兵; 黄凯

doi:10.11959/j.issn.2096-109x.2025047

您当前的位置：

首页 >

文章列表页 >

FL-IoV：基于联邦学习的综合车联网入侵检测方法

专题：新型工业化网络安全 | 更新时间：2025-09-12

- FL-IoV：基于联邦学习的综合车联网入侵检测方法
- FL-IoV: comprehensive intrusion detection method for internet of vehicles based on federated learning
- 网络与信息安全学报 2025年11卷第4期页码：127-140
- 作者机构：
  
  北京银联金卡科技有限公司深圳分公司，广东深圳 518049
- 作者简介：
  
  [ "蒋玉长（1998- ），男，广东广州人，北京银联金卡科技有限公司深圳分公司助理工程师、技术支持工程师，主要研究方向为数据安全、车联网安全、金融科技。" ]
  [ "蒋利兵（1986- ），男，湖南永州人，主要研究方向为终端机具产品安全、信息系统安全、网络通信安全、数据安全。" ]
  [ "黄凯（1995- ），男，广东潮州人，主要研究方向为数据安全、金融科技。" ]
- 基金信息：
- DOI：10.11959/j.issn.2096-109x.2025047
  中图分类号： TN915
- 收稿：2025-02-08，
  
  修回：2025-05-08，
  
  纸质出版：2025-08-25
- 稿件说明：
移动端阅览
蒋玉长, 蒋利兵, 黄凯. FL-IoV:基于联邦学习的综合车联网入侵检测方法[J]. 网络与信息安全学报, 2025, 11(4): 127-140.

Format: JIANG Y C, JIANG L B, HUANG K. FL-IoV: comprehensive intrusion detection method for internet of vehicles based on federated learning[J]. Chinese Journal of Network and Information Security, 2025, 11(4): 127-140.
蒋玉长, 蒋利兵, 黄凯. FL-IoV:基于联邦学习的综合车联网入侵检测方法[J]. 网络与信息安全学报, 2025, 11(4): 127-140. DOI： 10.11959/j.issn.2096-109x.2025047.

Format: JIANG Y C, JIANG L B, HUANG K. FL-IoV: comprehensive intrusion detection method for internet of vehicles based on federated learning[J]. Chinese Journal of Network and Information Security, 2025, 11(4): 127-140. DOI： 10.11959/j.issn.2096-109x.2025047.

摘要

现有车联网入侵检测系统面临计算开销过大及数据隐私限制两大挑战，难以高效部署与保障隐私。为此，提出一种基于联邦学习架构的车联网入侵检测方法FL-IoV，旨在于分布式边缘设备上协作完成检测任务，同时降低数据隐私泄露风险。通过将车载通信流量转化为图像并利用定制轻量级模型MobileNet-Tiny提取特征，FL-IoV在保证检测准确性的同时，可部署于资源受限设备。经在公开数据集Car-Hacking上验证，FL-IoV在本地环境和联邦环境下分别实现99.17%和98.51%的检测准确率，且在Raspberry Pi 4低算力设备上保持每个样本预测时间低于10 ms，表现出比现有方法更优的准确率和实时性。FL-IoV为车联网安全提供了一种既高效又保护隐私的入侵检测方案。

Abstract

Existing intrusion detection systems in the Internet of vehicles (IoV) were faced with two major challenges: excessive computational overhead and data privacy constraints

which had hindered efficient deployment and privacy protection. To address these issues

an IoV intrusion detection method based on a federated learning architecture

named FL-IoV

was proposed. It was designed to collaboratively accomplish detection tasks on distributed edge devices while the risk of data privacy breaches was reduced. Vehicular communication traffic within the IoV was converted into images

and a customized lightweight model

MobileNet-Tiny

was utilized to extract features

ensuring detection accuracy and enabling deployment on resource-constrained devices. When validated on the publicly available Car-Hacking dataset

FL-IoV achieved detection accuracies of 99.17% and 98.51% in local and federated IoV environments

respectively

and a per-sample prediction time of under 10 milliseconds was maintained on low-power devices such as the Raspberry Pi 4. These results demonstrate superior accuracy and real-time performance of FL-IoV compared to existing methods in IoV security. The successful application of FL-IoV provides an efficient and privacy-preserving new solution for IoV security.

关键词

Keywords

references

YANG L , MOUBAYED A , SHAMI A . MTH-IDS: a multitiered hybrid intrusion detection system for internet of vehicles [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 1 ): 616 - 632 .

潘桐 , 陈伟 , 吴礼发 . 面向不平衡样本的物联网入侵检测方法 [J ] . 网络与信息安全学报 , 2023 , 9 ( 1 ): 130 - 139 .

PAN T , CHEN W , WU L F . IoT intrusion detection method for unbalanced samples [J ] . Chinese Journal of Network and Information Security , 2023 , 9 ( 1 ): 130 - 139 .

罗文华 , 张晓龙 . 基于联邦学习与卷积神经网络的入侵检测模型 [J ] . 信息安全研究 , 2024 , 10 ( 7 ): 642 - 648 .

LUO W H , ZHANG X L . Model of intrusion detection based on federated learning and convolutional neural network [J ] . Journal of Information Security Research , 2024 , 10 ( 7 ): 642 - 648 .

SINGH N B , SINGH M M , SARKAR A , et al . A novel wide & deep transfer learning stacked GRU framework for network intrusion detection [J ] . Journal of Information Security and Applications , 2021 , 61 : 102899 .

NGUYEN M T , KIM K . Genetic convolutional neural network for intrusion detection systems [J ] . Future Generation Computer Systems , 2020 , 113 : 418 - 427 .

杨晓文 , 张健 , 况立群 , 等 . 融合CNN-BiGRU和注意力机制的网络入侵检测模型 [J ] . 信息安全研究 , 2024 , 10 ( 3 ): 202 - 208 .

YANG X W , ZHANG J , KUANG L Q , et al . A network intrusion detection model integrating CNN-BiGRU and attention mechanism [J ] . Journal of Information Security Research , 2024 , 10 ( 3 ): 202 - 208 .

郑诚波 , 闫皓楠 , 傅彩利 , 等 . 面向智能物联网的双层级联邦安全学习架构 [J ] . 网络与信息安全学报 , 2024 , 10 ( 6 ): 71 - 80 .

ZHENG C B , YAN H N , FU C L , et al . Double layer federated security learning architecture for artificial intelligence of things [J ] . Chinese Journal of Network and Information Security , 2024 , 10 ( 6 ): 71 - 80 .

XIE G Q , YANG L T , YANG Y D , et al . Threat analysis for automotive CAN networks: a GAN model-based intrusion detection technique [J ] . IEEE Transactions on Intelligent Transportation Systems , 2021 , 22 ( 7 ): 4467 - 4477 .

LO W , ALQAHTANI H , THAKUR K , et al . A hybrid deep learning based intrusion detection system using spatial-temporal representation of in-vehicle network traffic [J ] . Vehicular Communications , 2022 , 35 : 100471 .

JAVED A R , REHMAN S U , KHAN M U , et al . CANintelliIDS: detecting in-vehicle intrusion attacks on a controller area network using CNN and attention-based GRU [J ] . IEEE Transactions on Network Science and Engineering , 2021 , 8 ( 2 ): 1456 - 1466 .

MCMAHAN H B , MOORE E , RAMAGE D , et al . Communication- efficient learning of deep networks from decentralized data [EB ] . 2016 .

SONG H M , WOO J , KIM H K . In-vehicle network intrusion detection using deep convolutional neural network [J ] . Vehicular Communications , 2020 , 21 : 100198 .

HOWARD A , SANDLER M , CHEN B , et al . Searching for MobileNet V3 [C ] // Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE Press , 2019 : 1314 - 1324 .

TSAI T H , YU W T . BiSeNet V3: bilateral segmentation network with coordinate attention for real-time semantic segmentation [J ] . Neurocomputing , 2023 , 532 : 33 - 42 .

LAMPE B , MENG W Z . Can-train-and-test: a curated CAN dataset for automotive intrusion detection [J ] . Computers & Security , 2024 , 140 : 103777 .

TSAI T H , TSENG Y W . BiSeNet V3: bilateral segmentation network with coordinate attention for real-time semantic segmentation [J ] . Neurocomputing , 2023 , 532 : 33 - 42 .

LI B B , WU Y H , SONG J R , et al . DeepFed: federated deep learning for intrusion detection in industrial cyber-physical systems [J ] . IEEE Transactions on Industrial Informatics , 2021 , 17 ( 8 ): 5615 - 5624 .

HE C Y , SHAH A D , TANG Z H , et al . FedCV: a federated learning framework for diverse computer vision tasks [EB ] . 2021 .

QU L Q , ZHOU Y Y , LIANG P P , et al . Rethinking architecture design for tackling data heterogeneity in federated learning [C ] // Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE Press , 2022 : 10051 - 10061 .

DESTA A K , OHIRA S , ARAI I , et al . Rec-CNN: in-vehicle networks intrusion detection using convolutional neural networks trained on recurrence plots [J ] . Vehicular Communications , 2022 , 35 : 100470 .

HOANG T N , KIM D . Detecting in-vehicle intrusion via semi-supervised learning-based convolutional adversarial autoencoders [J ] . Vehicular Communications , 2022 , 38 : 100520 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向智能物联网的双层级联邦安全学习架构

联邦学习研究综述

基于深度循环神经网络和改进SMOTE算法的组合式入侵检测模型

DP-FedDRC：缓解维度坍塌的差分隐私个性化联邦学习

基于双路特征提取和自适应融合的钓鱼网站检测