基于深度学习的车联网的路网监测系统的DoS和DDoS攻击的入侵检测方法  

DEEP LEARNING BASED DOS AND DDOS ATTACK DETECTION METHOD IN THE HIGHWAY MONITORING SYSTEM OF IOV

作　　者：曹磊 温蜜 何蔚 Cao Lei;Wen Mi;He Wei(College of Computer Science and Technology,Shanghai University of Electric Power,Shanghai 200090,China)

机构地区：[1]上海电力大学计算机科学与技术学院,上海200090

出　　处：《计算机应用与软件》2025年第1期303-311,共9页Computer Applications and Software

基　　金：国家自然科学基金项目(61872230,61802248,61802249);上海市2019年度“科技创新行动计划”高新技术领域项目(19511103700)。

摘　　要：面对日益复杂的交通路况,车联网成为提升智能路网监测系统性能的重要保证,它可以实现车载网、车际网、车辆与移动互联网之间的信息交互共享。然而DoS和DDoS网络攻击的频发,成为车联网可用性的严重威胁之一。针对传统入侵检测算法存在训练困难、分类精度低、泛化能力差的问题,提出一种高效的深度学习模型CNN-BiSRU。实验选择在最新的CICIDS2018数据集中进行验证,结果表明,该模型获得了更高的检测精度,而相比于CNN-BiLSTM,CNN-BiSRU拥有更快的检测速度。Faced with the increasingly complex traffic conditions,the internet of vehicle(IoV)has become an important guarantee for improving the performance to monitor the intelligent highway network,which can realize information exchange and sharing between vehicle network,Internet,vehicle and mobile Internet.However,the increase of DoS and DDoS attacks has one of the most serious threats to the availability of IoV.Aimed at the problems of traditional intrusion detection algorithms such as training difficulties,low classification accuracy,and poor generalization ability,an efficient deep learning model CNN-BiSRU is proposed.The experiment was performed for verification in the latest CICIDS2018 data set.The results show that the model achieves higher detection accuracy,and CNN-BiSRU has a faster detection speed compared with CNN-BiLSTM.

关 键 词：入侵检测 DOS攻击 深度学习 车联网 路网监测系统 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]