计量学报2024，Vol.45Issue(9)：1407-1415,9.DOI:10.3969/j.issn.1000-1158.2024.09.20
基于CBAMTL-MobileNet V3的车载网络入侵检测
Vehicle Network Intrusion Detection Based on CBAMTL-MobileNet V3
摘要
Abstract
A vehicle network intrusion detection method is proposed based on CBAMTL-MobileNet V3.The lightweight MobileNet V3 model is used,and reduced its layers to improve both training and detection speeds.The squeeze-and-excitation(SE)modules in the model are replaced with convolutional block attention module(CBAM)to focus the model more on specific features,enhancing feature extraction capabilities and consequently improving the accuracy of attack detection.Transfer learning is introduced to fine-tune the model weights,reducing parameter and memory resource consumption,thereby shortening the training time and improving the computational speed of the model.Simulation results indicate that the proposed model is better than the MobileNet V3 model in various detection indexes.Compared with other models,the proposed model exhibits both the efficiency of a lightweight model and higher detection accuracy than other complex models,making it the optimal performer in recognizing various types of attacks.关键词
无线电计量/机器视觉/入侵检测/深度学习/轻量级模型/车载网络Key words
radio metrology/machine vision/intrusion detection/deep learning/lightweight model/vehicle network分类
通用工业技术引用本文复制引用
吴忠强,李孟亭..基于CBAMTL-MobileNet V3的车载网络入侵检测[J].计量学报,2024,45(9):1407-1415,9.基金项目
省级重点实验室绩效补助经费项目(22567612H) （22567612H）
