基于優(yōu)化數(shù)據(jù)處理的深度信念網(wǎng)絡(luò)模型的入侵檢測(cè)方法
發(fā)布時(shí)間:2018-10-19 06:40
【摘要】:針對(duì)目前網(wǎng)絡(luò)中存在的對(duì)已知攻擊類型的入侵檢測(cè)具有較高的檢測(cè)率,但對(duì)新出現(xiàn)的攻擊類型難以識(shí)別的缺陷問題,提出了一種基于優(yōu)化數(shù)據(jù)處理的深度信念網(wǎng)絡(luò)(DBN)模型的入侵檢測(cè)方法。該方法在不破壞已學(xué)習(xí)過的知識(shí)和不嚴(yán)重影響檢測(cè)實(shí)時(shí)性的基礎(chǔ)上,分別對(duì)數(shù)據(jù)處理和方法模型進(jìn)行改進(jìn),以解決上述問題。首先,將經(jīng)過概率質(zhì)量函數(shù)(PMF)編碼和MaxMin歸一化處理的數(shù)據(jù)應(yīng)用于DBN模型中;然后,通過固定其他參數(shù)不變而變化一種參數(shù)和交叉驗(yàn)證的方式選擇相對(duì)最優(yōu)的DBN結(jié)構(gòu)對(duì)未知攻擊類型進(jìn)行檢測(cè);最后,在NSL-KDD數(shù)據(jù)集上進(jìn)行了驗(yàn)證。實(shí)驗(yàn)結(jié)果表明,數(shù)據(jù)的優(yōu)化處理能夠使DBN模型提高分類精度,基于DBN的入侵檢測(cè)方法具有良好的自適應(yīng)性,對(duì)未知樣本具有較高的識(shí)別能力。在檢測(cè)實(shí)時(shí)性上,所提方法與支持向量機(jī)(SVM)算法和反向傳播(BP)網(wǎng)絡(luò)算法相當(dāng)。
[Abstract]:At present, the intrusion detection of known attack types in the network has a high detection rate, but it is difficult to identify the new attack types. An intrusion detection method based on (DBN) model based on optimized data processing is proposed. In order to solve the above problems, the method improves the data processing and the method model separately on the basis of not destroying the knowledge that has been learned and not seriously affecting the real-time detection. First, the data encoded by the probabilistic quality function (PMF) and normalized by MaxMin are applied to the DBN model. The unknown attack type is detected by fixing other parameters and changing one parameter and cross-validating method by selecting the relatively optimal DBN structure. Finally, the method is verified on the NSL-KDD data set. The experimental results show that the optimal processing of data can improve the classification accuracy of DBN model. The intrusion detection method based on DBN has good adaptability and high recognition ability to unknown samples. In real time detection, the proposed method is comparable to the support vector machine (SVM) (SVM) algorithm and the backpropagation (BP) network algorithm.
【作者單位】: 遼寧工程技術(shù)大學(xué)軟件學(xué)院;
【基金】:遼寧省教育廳科學(xué)技術(shù)研究項(xiàng)目(LJYL052)~~
【分類號(hào)】:TP393.08
[Abstract]:At present, the intrusion detection of known attack types in the network has a high detection rate, but it is difficult to identify the new attack types. An intrusion detection method based on (DBN) model based on optimized data processing is proposed. In order to solve the above problems, the method improves the data processing and the method model separately on the basis of not destroying the knowledge that has been learned and not seriously affecting the real-time detection. First, the data encoded by the probabilistic quality function (PMF) and normalized by MaxMin are applied to the DBN model. The unknown attack type is detected by fixing other parameters and changing one parameter and cross-validating method by selecting the relatively optimal DBN structure. Finally, the method is verified on the NSL-KDD data set. The experimental results show that the optimal processing of data can improve the classification accuracy of DBN model. The intrusion detection method based on DBN has good adaptability and high recognition ability to unknown samples. In real time detection, the proposed method is comparable to the support vector machine (SVM) (SVM) algorithm and the backpropagation (BP) network algorithm.
【作者單位】: 遼寧工程技術(shù)大學(xué)軟件學(xué)院;
【基金】:遼寧省教育廳科學(xué)技術(shù)研究項(xiàng)目(LJYL052)~~
【分類號(hào)】:TP393.08
【相似文獻(xiàn)】
相關(guān)期刊論文 前10條
1 吳新民;兩種典型的入侵檢測(cè)方法研究[J];計(jì)算機(jī)工程與應(yīng)用;2002年10期
2 魯宏偉,羅鋼;基于專家系統(tǒng)的入侵檢測(cè)方法[J];武鋼技術(shù);2003年01期
3 蔣盛益,李慶華,王卉,孟中樓;一種基于聚類的有指導(dǎo)的入侵檢測(cè)方法[J];小型微型計(jì)算機(jī)系統(tǒng);2005年06期
4 蔣盛益,李慶華;基于引力的入侵檢測(cè)方法[J];系統(tǒng)仿真學(xué)報(bào);2005年09期
5 麥永浩;劉志軍;薛琴;;電子警務(wù)的入侵檢測(cè)方法研究[J];湖北警官學(xué)院學(xué)報(bào);2005年05期
6 蔣盛益,李慶華;無(wú)指導(dǎo)的入侵檢測(cè)方法[J];計(jì)算機(jī)工程;2005年09期
7 蔣盛益;李慶華;;有指導(dǎo)的入侵檢測(cè)方法研究[J];通信學(xué)報(bào);2006年03期
8 王國(guó)棟;;入侵檢測(cè)方法淺析[J];科技創(chuàng)新導(dǎo)報(bào);2008年05期
9 黃鐵;劉巧梅;;基于模糊遺傳學(xué)習(xí)的入侵檢測(cè)方法[J];計(jì)算技術(shù)與自動(dòng)化;2008年03期
10 劉r,
本文編號(hào):2280438
本文鏈接:http://sikaile.net/guanlilunwen/ydhl/2280438.html
最近更新
教材專著