《電子技術(shù)應(yīng)用》
您所在的位置:首頁 > 通信與網(wǎng)絡(luò) > 設(shè)計應(yīng)用 > 基于輕量級密集神經(jīng)網(wǎng)絡(luò)的車載自組網(wǎng)入侵檢測方法
基于輕量級密集神經(jīng)網(wǎng)絡(luò)的車載自組網(wǎng)入侵檢測方法
2022年電子技術(shù)應(yīng)用第7期
黃學(xué)臻1,,翟 翟2,,周 琳2,祝雅茹2
1.公安部第一研究所,,北京100044,;2.北京交通大學(xué) 智能交通數(shù)據(jù)安全與隱私保護技術(shù)北京市重點實驗室,北京100044
摘要: 在車載自組網(wǎng)中,,攻擊者可以通過偽造,、篡改消息等方式發(fā)布虛假交通信息,,導(dǎo)致交通擁堵甚至是嚴(yán)重的交通事故,而傳統(tǒng)的入侵檢測方法不能滿足車載自組網(wǎng)的應(yīng)用需求,。為了解決現(xiàn)階段車載網(wǎng)中入侵檢測方法性能低且存儲與時間成本高的問題,,提出了一種基于密集神經(jīng)網(wǎng)絡(luò)的入侵檢測方法L-DenseNet(Light Dense Neural Network),通過降低模型復(fù)雜性,,提升算法訓(xùn)練速度和部署適應(yīng)性,,使其更適用于車載自組網(wǎng)中的入侵檢測。在VeReMi數(shù)據(jù)集上進行對比實驗,,結(jié)果表明,,該方法在識別各類攻擊的精確率和召回率的綜合表現(xiàn)最好,且具有較少的時間成本和存儲開銷,。
中圖分類號: TN915.08
文獻標(biāo)識碼: A
DOI:10.16157/j.issn.0258-7998.222843
中文引用格式: 黃學(xué)臻,,翟翟,周琳,,等. 基于輕量級密集神經(jīng)網(wǎng)絡(luò)的車載自組網(wǎng)入侵檢測方法[J].電子技術(shù)應(yīng)用,,2022,48(7):67-73.
英文引用格式: Huang Xuezhen,,Zhai Di,,Zhou Lin,et al. Intrusion detection method for VANET based on light dense neural network[J]. Application of Electronic Technique,,2022,,48(7):67-73.
Intrusion detection method for VANET based on light dense neural network
Huang Xuezhen1,Zhai Di2,,Zhou Lin2,,Zhu Yaru2
1.The First Research Institution of Ministry of Public Security of PRC,Beijing 100044,,China,; 2.Security and Privacy in Intelligent Transportation,Beijing Jiaotong University,,Beijing 100044,,China
Abstract: In the vehicular ad-hoc network, attackers can publish false traffic information by forging or tampering with messages, etc., resulting in traffic congestion or even serious traffic accidents. However, traditional intrusion detection methods cannot meet the application requirements of vehicular ad-hoc network. In order to solve the problems such as low performance, instability and high storage and time cost of intrusion detection methods in the current vehicular ad-hoc network, this paper proposes an intrusion detection method L-DenseNet(Light Dense Neural Network) based on dense neural network. The L-DenseNet is proposed to reduce the complexity of the model and improve the training speed and deployment adaptability of the detection algorithm. The proposed method is more suitable for intrusion detection in vehicle ad hoc networks. This paper conducts comparative experiments on the VeReMi dataset. The results show that the method proposed has the best overall performance in identifying various types of attacks in terms of precision and recall. As the same time, this method has less time cost and storage overhead.
Key words : vehicular ad-hoc network;dense neural network,;intrusion detection,;deep learning

0 引言

    隨著當(dāng)前車輛激增,交通擁堵及交通事故等嚴(yán)重影響了社會生活,,為了滿足人們對于提升出行質(zhì)量的需求,,車載自組網(wǎng)(Vehicular Ad-Hoc Network,VANET),,簡稱車載網(wǎng),,逐漸成為實現(xiàn)智能交通系統(tǒng)的基礎(chǔ)之一,。雖然VANET能夠為人們的出行質(zhì)量提供有力保障,但是大量的車輛數(shù)據(jù)通過無線通信共享,,任何交換惡意信息的節(jié)點都會損害網(wǎng)絡(luò)安全性,,因此,VANET的安全性成為了車聯(lián)網(wǎng)領(lǐng)域的重點研究目標(biāo),。

    為了提高VANET安全性,,避免入侵行為產(chǎn)生的危害,首先需要明確其面臨的安全問題,。VANET中入侵行為主要源自于自私的駕駛者和惡意的攻擊者,自私的駕駛者主要是為了私利而獨享道路,、節(jié)約自身資源等,;惡意的攻擊者使車輛無意或有意地在網(wǎng)絡(luò)中傳輸不正確的信息(例如錯誤的位置或速度坐標(biāo)),影響車載網(wǎng)的正常工作,,威脅駕乘者的生命財產(chǎn)安全[1],。然而,面對日益復(fù)雜的車載網(wǎng)絡(luò)環(huán)境,,傳統(tǒng)的入侵檢測方法呈現(xiàn)出相當(dāng)多的問題,。其中最主要的問題是:大數(shù)據(jù)背景下傳統(tǒng)入侵檢測方法性能低下,存儲與時間成本高,,準(zhǔn)確性不高,。




本文詳細(xì)內(nèi)容請下載:http://forexkbc.com/resource/share/2000004589




作者信息:

黃學(xué)臻1,,翟  翟2,,周  琳2,祝雅茹2

(1.公安部第一研究所,,北京100044,;2.北京交通大學(xué) 智能交通數(shù)據(jù)安全與隱私保護技術(shù)北京市重點實驗室,北京100044)




wd.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),,未經(jīng)授權(quán)禁止轉(zhuǎn)載,。