【摘要】：現(xiàn)在，網(wǎng)絡(luò)已經(jīng)成為了人們生活中最重要的角色之一，同時(shí)各種安全問(wèn)題也應(yīng)運(yùn)而生。在這個(gè)背景下，針對(duì)網(wǎng)絡(luò)的數(shù)字取證問(wèn)題已經(jīng)成為了當(dāng)下的熱點(diǎn)。同時(shí)，云計(jì)算技術(shù)的興起，為數(shù)字取證問(wèn)題所遇到的困難，提供了新的解決辦法。云計(jì)算技術(shù)解決大規(guī)模數(shù)據(jù)上的能力是有目共睹的，這一新的技術(shù)產(chǎn)生，提供了一種新的計(jì)算服務(wù)和存儲(chǔ)服務(wù)形式。本文將云計(jì)算技術(shù)引入到以網(wǎng)絡(luò)流量為目標(biāo)的數(shù)字取證問(wèn)題中，首先對(duì)云計(jì)算的背景知識(shí)和數(shù)字取證的背景知識(shí)進(jìn)行了概要介紹，并著重描述了Hadoop2.2的優(yōu)勢(shì)，以及選擇這一版本作為基礎(chǔ)平臺(tái)的原因；其次對(duì)map-reduce和yarn架構(gòu)進(jìn)行了闡述，給出了基于云計(jì)算的網(wǎng)絡(luò)流量數(shù)字取證模型，并對(duì)前人提出的分布式SVM算法進(jìn)行了總結(jié)，以之前的算法作為基礎(chǔ)，提出了一種改進(jìn)后分布式SVM算法作為網(wǎng)絡(luò)流量算法，經(jīng)過(guò)實(shí)驗(yàn)驗(yàn)證了其有效性和準(zhǔn)確性，并給出了實(shí)驗(yàn)過(guò)程和結(jié)果，證明了這個(gè)分布式算法能夠在保證準(zhǔn)確性的前提下，在一定程度上提高流量分析的效率和性能；最后，對(duì)本文的工作進(jìn)行了總結(jié)，，并對(duì)應(yīng)用云計(jì)算的數(shù)字取證背景進(jìn)行了展望。
[Abstract]:Now, the network has become one of the most important roles in people's life, at the same time, a variety of security problems have emerged. In this context, digital forensics for the network has become a hot spot. At the same time, the rise of cloud computing technology provides a new solution to the problem of digital forensics. The ability of cloud computing technology to solve large-scale data is obvious. This new technology has provided a new form of computing and storage services. In this paper, cloud computing technology is introduced into digital forensics with network traffic as its target. Firstly, the background knowledge of cloud computing and the background knowledge of digital forensics are briefly introduced, and the advantages of Hadoop2.2 are described emphatically. And the reasons for choosing this version as the base platform; Secondly, the architecture of map-reduce and yarn is expatiated, and the network traffic digital forensics model based on cloud computing is given, and the distributed SVM algorithm proposed by predecessors is summarized, which is based on the previous algorithms. An improved distributed SVM algorithm is proposed as a network traffic algorithm. The validity and accuracy of the algorithm are verified by experiments, and the experimental process and results are given. It is proved that this distributed algorithm can ensure the accuracy of the algorithm. Improve the efficiency and performance of flow analysis to a certain extent; Finally, the work of this paper is summarized, and the application of cloud computing digital forensics background is prospected.
【學(xué)位授予單位】：吉林大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP393.08

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 丁世飛;齊丙娟;譚紅艷;;支持向量機(jī)理論與算法研究綜述[J];電子科技大學(xué)學(xué)報(bào);2011年01期

2 李蓉 ,葉世偉 ,史忠植;SVM-KNN分類器——一種提高SVM分類精度的新方法[J];電子學(xué)報(bào);2002年05期

3 李建江;崔健;王聃;嚴(yán)林;黃義雙;;MapReduce并行編程模型研究綜述[J];電子學(xué)報(bào);2011年11期

4 許榕生;;國(guó)際計(jì)算機(jī)取證的操作規(guī)程標(biāo)準(zhǔn)化動(dòng)態(tài)[J];金融電子化;2003年09期

5 鄧河;陽(yáng)愛民;劉永定;;一種基于SVM的P2P網(wǎng)絡(luò)流量分類方法[J];計(jì)算機(jī)工程與應(yīng)用;2008年14期

6 曾聯(lián)明;吳湘濱;劉鵬;;網(wǎng)格環(huán)境下分布式SVM遙感圖像分類器模型研究[J];計(jì)算機(jī)工程與應(yīng)用;2009年05期

7 楊嶸,張國(guó)清,韋衛(wèi),李仰耀;基于NetFlow流量分析的網(wǎng)絡(luò)攻擊行為發(fā)現(xiàn)[J];計(jì)算機(jī)工程;2005年13期

8 許榕生;;中國(guó)數(shù)字取證的發(fā)展現(xiàn)狀[J];中國(guó)教育網(wǎng)絡(luò);2007年08期

9 宋暉;薛云;張良均;;基于SVM分類問(wèn)題的核函數(shù)選擇仿真研究[J];計(jì)算機(jī)與現(xiàn)代化;2011年08期

10 程學(xué)云;徐慧;朱玲玲;;基于SVM的分布式入侵檢測(cè)系統(tǒng)[J];南通大學(xué)學(xué)報(bào)(自然科學(xué)版);2008年03期

相關(guān)博士學(xué)位論文 前1條

1 張有東;網(wǎng)絡(luò)取證技術(shù)研究[D];南京航空航天大學(xué);2007年

本文編號(hào)：2383962