隨著互聯(lián)網(wǎng)技術(shù)的迅猛發(fā)展,以及云計(jì)算與移動(dòng)智能終端技術(shù)的相互融合產(chǎn)生了移動(dòng)云計(jì)算（Mobile Cloud Computing,MCC）,并引起學(xué)術(shù)界和工業(yè)界的廣泛關(guān)注。根據(jù)2016年思科IBSG數(shù)據(jù)顯示,全球近85%的人口都在使用移動(dòng)終端設(shè)備。然而,由于MCC具有分布式、用戶訪問量大和操作簡便等特性,入侵者亦可在無管理員授權(quán)的情況下使用云計(jì)算和云存儲等服務(wù)。針對移動(dòng)云計(jì)算中的安全問題,許多研究學(xué)者采用防火墻技術(shù)和入侵檢測系統(tǒng)（Intrusion Detection System,IDS）等網(wǎng)絡(luò)信息安全技術(shù)來保障移動(dòng)云計(jì)算安全。但現(xiàn)有研究依然存在較多的安全問題,如防火墻技術(shù)可擴(kuò)展性和自適應(yīng)性較差,IDS的檢測精度低、誤報(bào)率高以及數(shù)據(jù)屬性冗余等問題。針對現(xiàn)有IDS存在的上述問題,論文采用基于分類和信息論的機(jī)器學(xué)習(xí)方法構(gòu)建了入侵檢測系統(tǒng)的入侵檢測模型。論文采用的基于分類的機(jī)器學(xué)習(xí)方法和特征選擇方法包括:支持向量機(jī)（Support Vector Machine,SVM）,隨機(jī)森林（Random Forest,RF）,信息增益（Information Gain,IG）和用于進(jìn)化特征選擇的Map... 

【文章來源】：蘭州理工大學(xué)甘肅省

【文章頁數(shù)】：97 頁

【學(xué)位級別】：碩士

【文章目錄】：
中文摘要
Abstract
1.Introduction
    1.1 Research Background and Significance
    1.2 Research Status for Related Works
        1.2.1 Intrusion detection system（IDS）
        1.2.2 Feature selection method
        1.2.3 MapReduce for evolutionary feature selection（MR-EFS）
        1.2.4 Dataset description
    1.3 Research Innovations and Main Objectives
    1.4 Organization Structure and Arrangement
2.Related Concepts and Basic Principles
    2.1 Mobile Intelligent Terminal based Cloud Computing
        2.1.1 Overview of cloud computing
        2.1.2 Concept of mobile cloud computing（MCC）
    2.2 Intrusion Detection System
        2.2.1 Basic concept of intrusion detection system
        2.2.2 Intrusion detection framework
        2.2.3 Intrusion detection performance metrics
    2.3 Feature Selection Method
        2.3.1 Information gain（IG）based feature selection
        2.3.2 MapReduce for evolutionary feature selection（MR-EFS）
    2.4 Support Vector Machine（SVM）
    2.5 Random Forest（RF）Classifier
    2.6 Brief Summary
3.Intrusion Detection Method Based on SVM and Information Gain for Mobile Cloud Computing
    3.1 Introduction
    3.2 Intrusion Detection Method based on SVM and IG for MCC
    3.3 Experimental Results and Analysis
        3.3.1 Dataset and data preprocessing
        3.3.2 Information gain based feature selection method
        3.3.3 Performance metrics
        3.3.4 Performance evaluation
        3.3.5 Experimental result and discussion
    3.4 Brief Summary
4.Intrusion Detection Method for MCC based on MapReduce for Evolutionary Feature Selection
    4.1 Introduction
    4.2 Implementation of Random Forest Classifier Integrated with IDS Model
    4.3 Experimental Results and Analysis
        4.3.1 Dataset collection and data preprocessing
        4.3.2 MapReduce for evolutionary feature selection
        4.3.3 Performance metrics
        4.3.4 Experimental result and discussion
    4.4 Brief Summary
Conclusions and Future work
References
Acknowledgement
Appendix A.Academic papers published during the master's degree program
Appendix B.Key Codes used in this thesis


【參考文獻(xiàn)】：
期刊論文
[1]融合FAST特征選擇與ABQGSA-SVM的網(wǎng)絡(luò)入侵檢測[J]. 李叢,閆仁武,朱長水,高廣銀.  計(jì)算機(jī)應(yīng)用研究. 2017(07)
[2]Intrusion Detection Algorithm Based on Density,Cluster Centers,and Nearest Neighbors[J]. Xiujuan Wang,Chenxi Zhang,Kangfeng Zheng.  中國通信. 2016(07)
[3]基于云計(jì)算的移動(dòng)智能終端入侵檢測方法研究[J]. 李慧芳,彭新光.  計(jì)算機(jī)仿真. 2016(03)
[4]基于PCA的SVM網(wǎng)絡(luò)入侵檢測研究[J]. 戚名鈺,劉銘,傅彥銘.  信息網(wǎng)絡(luò)安全. 2015(02)
[5]云模型半監(jiān)督聚類動(dòng)態(tài)加權(quán)的入侵檢測方法[J]. 張杰,李永忠.  昆明理工大學(xué)學(xué)報(bào)(自然科學(xué)版). 2013(04)

碩士論文
[1]基于云端的移動(dòng)智能終端入侵檢測機(jī)制研究[D]. 趙雪.遼寧大學(xué) 2015



本文編號：3004957