本文選題：入侵檢測 + BP神經(jīng)網(wǎng)絡(luò)��； 參考：《解放軍信息工程大學(xué)》2014年碩士論文

【摘要】：由于網(wǎng)絡(luò)本身開放性和自由性的特點(diǎn),導(dǎo)致一些非法分子的攻擊,惡意破壞或侵犯網(wǎng)絡(luò),安全問題日趨突出。攻擊網(wǎng)絡(luò)的手段和技術(shù)不斷更新,使得傳統(tǒng)的防火墻、數(shù)字認(rèn)證等安全防護(hù)措施已經(jīng)不能滿足網(wǎng)絡(luò)安全的需求,入侵檢測技術(shù)應(yīng)運(yùn)而生。然而由于入侵檢測算法的局限性,目前的入侵檢測系統(tǒng)仍然存在實(shí)時(shí)性差、誤報(bào)率高等不足。本文分析傳統(tǒng)BP神經(jīng)網(wǎng)絡(luò)構(gòu)建入侵檢測模型在收斂速度和漏報(bào)率方面存在的缺陷,提出將改進(jìn)的粒子群算法應(yīng)用到入侵檢測系統(tǒng)中；通過研究Probing和Dos的攻擊原理,分析這Dos攻擊方法的特征,提取特征數(shù)據(jù),建立特征集合,設(shè)計(jì)一種基于改進(jìn)PSO和BP神經(jīng)網(wǎng)絡(luò)的入侵檢測模型,并在此模型的基礎(chǔ)設(shè)計(jì)網(wǎng)絡(luò)入侵檢測系統(tǒng),通過仿真試驗(yàn)證明系統(tǒng)在誤報(bào)率、收斂速度及漏報(bào)率方面的改進(jìn)效果。本文所作的主要研究工作包括以下內(nèi)容：(1)分析標(biāo)準(zhǔn)粒子群算法與基本BP神經(jīng)網(wǎng)絡(luò)構(gòu)建入侵檢測模型存在的不足,通過引入慣性權(quán)重因子、動(dòng)態(tài)收縮因子、變異操作和多目標(biāo)尋優(yōu)等策略改進(jìn)粒子群算法,將和改進(jìn)后的粒子群算法優(yōu)化BP神經(jīng)網(wǎng)絡(luò)。(2)利用MATLAB工具進(jìn)行BP神經(jīng)網(wǎng)絡(luò)的設(shè)計(jì),從KDDCUP的數(shù)據(jù)集中提取訓(xùn)練數(shù)據(jù)和測試數(shù)據(jù),對神經(jīng)網(wǎng)絡(luò)進(jìn)行訓(xùn)練。(3)將訓(xùn)練好的BP神經(jīng)網(wǎng)絡(luò)用于入侵檢測,構(gòu)建基于優(yōu)化BP神經(jīng)網(wǎng)絡(luò)的入侵檢測系統(tǒng),為了提高系統(tǒng)的防御能力,通過系統(tǒng)與防火墻、殺毒軟件、反間諜軟件等的聯(lián)動(dòng),建立全方位的系統(tǒng)防護(hù)體系,使系統(tǒng)具有主動(dòng)防御的能力。最后設(shè)計(jì)實(shí)驗(yàn)環(huán)境和平臺(tái),對基于改進(jìn)PSO-BP神經(jīng)網(wǎng)絡(luò)的入侵檢測系統(tǒng)進(jìn)行性能分析,驗(yàn)證系統(tǒng)在檢測Probing攻擊和Dos攻擊方面的檢測能力,并將其與傳統(tǒng)的BP神經(jīng)網(wǎng)絡(luò)進(jìn)行對比。實(shí)驗(yàn)結(jié)果表明,基于改進(jìn)PSO-BP神經(jīng)網(wǎng)絡(luò)的入侵檢測系統(tǒng)能夠有效在阻止來自網(wǎng)絡(luò)上的惡意攻擊,提高了檢測的效率和處理性能,降低了漏報(bào)率和誤報(bào)率；同時(shí)也證明了改進(jìn)PSO-BP申經(jīng)網(wǎng)絡(luò)用于入侵檢測的可行性。
[Abstract]:Because of the openness and freedom of the network, some illegal elements attack, maliciously destroy or violate the network, and the security problem becomes more and more serious. The means and technology of attacking network are constantly updated, which makes traditional security measures such as firewall, digital authentication and so on can not meet the needs of network security. Intrusion detection technology emerges as the times require. However, due to the limitations of intrusion detection algorithm, the current intrusion detection system still has poor real-time performance and high false alarm rate. This paper analyzes the shortcomings of the traditional BP neural network in constructing intrusion detection model in terms of convergence speed and false report rate, and proposes to apply the improved particle swarm optimization algorithm to the intrusion detection system, and studies the attack principle of probe and Dos. This paper analyzes the features of the Dos attack method, extracts the feature data, establishes the feature set, designs an intrusion detection model based on improved PSO and BP neural network, and designs a network intrusion detection system based on this model. Simulation results show that the system can improve the false alarm rate, convergence rate and false alarm rate. The main research work in this paper includes the following contents: 1) analyzing the shortcomings of standard particle swarm optimization algorithm and basic BP neural network in constructing intrusion detection model. By introducing inertia weight factor and dynamic shrinkage factor, Mutation operation and multi-objective optimization are used to improve particle swarm optimization. The improved particle swarm optimization algorithm is used to optimize BP neural network. MATLAB is used to design BP neural network. The training data and test data are extracted from the data set of KDDCUP. The BP neural network is used in intrusion detection, and an intrusion detection system based on optimized BP neural network is constructed. In order to improve the defense ability of the system, antivirus software is used through the system and firewall. The linkage of anti-spyware software, the establishment of an all-round system protection system, so that the system has the ability of active defense. Finally, the experimental environment and platform are designed to analyze the performance of intrusion detection system based on improved PSO-BP neural network, and verify the detection ability of the system in detecting probe attack and dos attack, and compare it with the traditional BP neural network. The experimental results show that the intrusion detection system based on improved PSO-BP neural network can effectively prevent malicious attacks from the network, improve the detection efficiency and processing performance, and reduce the false alarm rate and false alarm rate. At the same time, it also proves the feasibility of improving PSO-BP network for intrusion detection.
【學(xué)位授予單位】：解放軍信息工程大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP393.08;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張寶X;張寶一;;基于BP神經(jīng)網(wǎng)絡(luò)的非線性函數(shù)擬合[J];電腦知識(shí)與技術(shù);2012年27期

2 井小沛;汪厚祥;聶凱;羅志偉;;面向入侵檢測的基于IMGA和MKSVM的特征選擇算法[J];計(jì)算機(jī)科學(xué);2012年07期

3 牟琦;畢孝儒;厙向陽;;基于GQPSO算法的網(wǎng)絡(luò)入侵特征選擇方法[J];計(jì)算機(jī)工程;2011年14期

4 吳曉軍;楊戰(zhàn)中;趙明;;均勻搜索粒子群算法[J];電子學(xué)報(bào);2011年06期

5 馮雪;裴志松;;粒子群優(yōu)化算法的研究與應(yīng)用[J];吉林建筑工程學(xué)院學(xué)報(bào);2011年03期

6 趙宏;;基于GA的BP神經(jīng)網(wǎng)絡(luò)在本安參數(shù)評(píng)定中的應(yīng)用[J];自動(dòng)化儀表;2011年04期

7 張濤;;校園網(wǎng)中入侵檢測系統(tǒng)的實(shí)驗(yàn)研究[J];電腦編程技巧與維護(hù);2011年04期

8 陳仕濤;陳國龍;郭文忠;劉延華;;基于粒子群優(yōu)化和鄰域約簡的入侵檢測日志數(shù)據(jù)特征選擇[J];計(jì)算機(jī)研究與發(fā)展;2010年07期

9 何紹榮;梁金明;何志勇;;基于互信息和關(guān)系積理論的特征選擇方法[J];計(jì)算機(jī)工程;2010年13期

10 張紅梅;范明鈺;;模式匹配BM算法改進(jìn)[J];計(jì)算機(jī)應(yīng)用研究;2009年09期

，

本文編號(hào)：2039635