【摘要】：移動(dòng)自組織網(wǎng)絡(luò)在無(wú)線通信領(lǐng)域得到了越來(lái)越廣泛的應(yīng)用,但其固有特性使其容易受到各種各樣的入侵,對(duì)其安全性研究是非常有價(jià)值的。入侵檢測(cè)技術(shù)作為一種主動(dòng)式安全防護(hù)機(jī)制,是保障移動(dòng)自組織網(wǎng)絡(luò)安全的關(guān)鍵。深度學(xué)習(xí)主要探討多層人工神經(jīng)網(wǎng)絡(luò)的建模和學(xué)習(xí)問(wèn)題,已經(jīng)在語(yǔ)音、圖像識(shí)別等領(lǐng)域獲得了巨大成功,為解決移動(dòng)自組織網(wǎng)絡(luò)入侵檢測(cè)這樣一個(gè)復(fù)雜的行為識(shí)別問(wèn)題提供了新的有效途徑。針對(duì)移動(dòng)自組織網(wǎng)絡(luò)安全問(wèn)題的多樣性和復(fù)雜性,本文提出了一種基于深度信念網(wǎng)絡(luò)(Deep Belief Network,DBN)的入侵檢測(cè)方法。DBN是一種比較成熟的深度學(xué)習(xí)模型,將DBN應(yīng)用于移動(dòng)自組織網(wǎng)絡(luò)入侵檢測(cè)技術(shù)中,能夠取得較高的檢測(cè)正確率。本文的主要工作和貢獻(xiàn)在于:結(jié)合移動(dòng)自組織網(wǎng)絡(luò)的特點(diǎn)和安全威脅,本文首先分析了入侵檢測(cè)技術(shù)應(yīng)用于移動(dòng)自組織網(wǎng)絡(luò)面臨的難題、幾種典型的入侵檢測(cè)算法和模型。研究了DBN模型的學(xué)習(xí)原理,受限玻爾茲曼機(jī)的訓(xùn)練算法;分析了將DBN應(yīng)用于移動(dòng)自組織網(wǎng)絡(luò)入侵檢測(cè)技術(shù)中原理上的可行性。其次,本文設(shè)計(jì)了基于DBN的移動(dòng)自組織網(wǎng)絡(luò)入侵檢測(cè)模型的體系結(jié)構(gòu),包括對(duì)無(wú)線數(shù)據(jù)包捕獲,數(shù)據(jù)預(yù)處理,模型訓(xùn)練和入侵檢測(cè)等模塊的詳細(xì)設(shè)計(jì);給出了DBN模型訓(xùn)練過(guò)程中會(huì)遇到的幾個(gè)問(wèn)題的解決方法。最后,對(duì)本文提出的基于DBN的移動(dòng)自組織網(wǎng)絡(luò)入侵檢測(cè)方法進(jìn)行了仿真。針對(duì)移動(dòng)自組織網(wǎng)絡(luò)路由層的拒絕服務(wù)攻擊,本文在NS2中添加了黑洞節(jié)點(diǎn)和自私節(jié)點(diǎn),模擬兩種網(wǎng)絡(luò)入侵。分別對(duì)正常網(wǎng)絡(luò)和加入攻擊節(jié)點(diǎn)的網(wǎng)絡(luò)進(jìn)行了仿真,分析了網(wǎng)絡(luò)性能,并提取了網(wǎng)絡(luò)行為特征�；贛ATLAB仿真了DBN入侵檢測(cè)模型,并對(duì)其進(jìn)行訓(xùn)練和測(cè)試。測(cè)試結(jié)果驗(yàn)證了本文提出的基于DBN的移動(dòng)自組織網(wǎng)絡(luò)入侵檢測(cè)方法的可行性;與傳統(tǒng)BP神經(jīng)網(wǎng)絡(luò)入侵檢測(cè)方法進(jìn)行比較,DBN具有更好的入侵檢測(cè)性能。
[Abstract]:Mobile ad hoc networks have been more and more widely used in the field of wireless communication, but their inherent characteristics make them vulnerable to various kinds of intrusion, so it is very valuable to study their security. As an active security protection mechanism, intrusion detection technology is the key to ensure the security of mobile ad hoc networks. Depth learning mainly discusses the modeling and learning problems of multi-layer artificial neural networks, and has been a great success in speech, image recognition and other fields. It provides a new and effective way to solve the complex behavior recognition problem of mobile ad hoc network intrusion detection. In view of the diversity and complexity of security problems in mobile ad hoc networks, this paper proposes an intrusion detection method based on deep belief network (Deep Belief Network,DBN). DBN is a mature deep learning model. The application of DBN in mobile ad hoc network intrusion detection technology can achieve a high detection accuracy. The main work and contributions of this paper are as follows: considering the characteristics and security threats of mobile ad hoc networks, this paper first analyzes the problems faced by the application of intrusion detection technology in mobile ad hoc networks, and several typical intrusion detection algorithms and models. The learning principle of DBN model and the training algorithm of constrained Boltzmann machine are studied, and the feasibility of applying DBN to mobile ad hoc network intrusion detection technology is analyzed. Secondly, this paper designs the architecture of mobile ad hoc network intrusion detection model based on DBN, including the detailed design of wireless packet capture, data preprocessing, model training and intrusion detection module. Some solutions to the problems encountered in DBN model training are given. Finally, the proposed intrusion detection method based on DBN in mobile ad hoc networks is simulated. In view of the denial of service attack in the routing layer of mobile ad hoc networks, black hole nodes and selfish nodes are added to NS2 to simulate the two kinds of network intrusion. The normal network and the network with attack nodes are simulated, the network performance is analyzed, and the network behavior characteristics are extracted. The DBN intrusion detection model is simulated, trained and tested based on MATLAB. The test results verify the feasibility of the proposed mobile ad hoc network intrusion detection method based on DBN, and compared with the traditional BP neural network intrusion detection method, DBN has better intrusion detection performance.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TN915.08

【共引文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳顯濤;金偉祖;于志安;;基于NS3的虛擬網(wǎng)絡(luò)實(shí)驗(yàn)室構(gòu)建及可視化實(shí)現(xiàn)[J];電腦知識(shí)與技術(shù);2014年01期

2 楊璐;;ZigBee路由協(xié)議算法的研究[J];電子科技;2014年03期

3 陳建建;高瑩;;WSN中LEACH和LEACH-C、MTE協(xié)議性能比較[J];工業(yè)控制計(jì)算機(jī);2014年03期

4 王秀瑋;劉旭東;;TFRC擁塞控制算法的改進(jìn)研究[J];德州學(xué)院學(xué)報(bào);2014年06期

5 王亞;熊焰;龔旭東;陸琦瑋;;基于模糊數(shù)學(xué)的MANET惡意節(jié)點(diǎn)識(shí)別[J];計(jì)算機(jī)工程;2014年05期

6 倪梁方;陳建建;;基于NS2的CBRP協(xié)議構(gòu)建與仿真研究[J];安徽工業(yè)大學(xué)學(xué)報(bào)(自然科學(xué)版);2014年03期

7 劉慶龍;高航;;LEACH協(xié)議在礦井環(huán)境監(jiān)測(cè)系統(tǒng)中的改進(jìn)[J];計(jì)算機(jī)與數(shù)字工程;2014年08期

8 朱昶勝;楊青;王杰;馮文芳;;基于城市交通場(chǎng)景的仿真研究[J];計(jì)算機(jī)仿真;2014年04期

9 王林;申莎莎;;無(wú)線傳感器網(wǎng)絡(luò)BMAC協(xié)議的研究與改進(jìn)[J];計(jì)算機(jī)工程與應(yīng)用;2014年19期

10 趙西洋;;淺談視頻傳輸質(zhì)量的影響因素[J];信息通信;2014年11期

相關(guān)碩士學(xué)位論文 前10條

1 張艷華;水下傳感器網(wǎng)絡(luò)路由算法的研究與設(shè)計(jì)[D];中國(guó)海洋大學(xué);2010年

2 趙欣;遺傳算法及其在路由優(yōu)化問(wèn)題中的應(yīng)用[D];寧波大學(xué);2009年

3 李苗苗;基于無(wú)線網(wǎng)絡(luò)的建筑能耗監(jiān)測(cè)系統(tǒng)研究[D];安徽理工大學(xué);2013年

4 魯玉定;面向藍(lán)藻監(jiān)測(cè)的無(wú)線傳感器網(wǎng)絡(luò)路由協(xié)議的研究[D];安徽工程大學(xué);2013年

5 劉周龍;基于船聯(lián)網(wǎng)的QoS保障技術(shù)的研究[D];武漢理工大學(xué);2013年

6 張春曉;基于IEEE 802.22的認(rèn)知網(wǎng)絡(luò)接入控制研究[D];北京交通大學(xué);2014年

7 周凱;基于機(jī)會(huì)轉(zhuǎn)發(fā)的Ad hoc網(wǎng)絡(luò)無(wú)干擾多徑路由協(xié)議研究[D];南京理工大學(xué);2014年

8 石海霞;面向機(jī)器人定位的無(wú)線傳感器網(wǎng)絡(luò)系統(tǒng)的研究與設(shè)計(jì)[D];南京理工大學(xué);2013年

9 趙奉安;基于MPLS流量工程的可區(qū)分服務(wù)故障恢復(fù)問(wèn)題研究[D];東北大學(xué);2011年

10 熊為;基于地理位置預(yù)測(cè)的Ad Hoc網(wǎng)絡(luò)洪泛控制路由協(xié)議研究[D];東北大學(xué);2013年

，

本文編號(hào)：2319257