预览加载中，请您耐心等待几秒...

基于粒子群优化和邻域约简的入侵检测日志数据特征选择.docx

预览
1/3
2/3
3/3

在线预览结束，喜欢就下载吧，查找使用更方便

下载提示 文本预览

如果您无法下载资料，请参考说明：

1、部分资料下载需要金币，请确保您的账户上有足够的金币

2、已购买过的文档，再次下载不重复扣费

3、资料包下载后请先用软件解压，在使用对应软件打开

基于粒子群优化和邻域约简的入侵检测日志数据特征选择 Abstract: Intrusiondetectionisanimportantresearchfieldinthefieldofcomputerandnetworksecurity.However,asthesizeofdatasetsgrows,selectingthemostimportantfeaturesfromthedatabecomesachallengingtask.Thispaperproposesafeatureselectionmethodbasedonparticleswarmoptimizationandneighborhoodreductionforintrusiondetectionlogdata.Theproposedmethodcombinestheadvantagesofparticleswarmoptimizationandneighborhoodreductiontoreducethedimensionalityofthefeaturesetandimprovetheclassificationaccuracy.Experimentswereconductedontworeal-worlddatasets,andtheresultsshowedthattheproposedmethodcaneffectivelyreducethedimensionalityofthedataandimproveclassificationaccuracy,comparedwithotherfeatureselectionmethods. Introduction: Intrusiondetectionisanimportantresearchfieldincomputerandnetworksecurity.Withtheincreasinglywidespreaduseofnetworkandcomputersystems,thenumberandseverityofattacksarerisingrapidly.Intrusiondetectionistheprocessofdetectingchangesinthecomputersystemornetworkthatindicateanunauthorizedattempttoaccessordamagethesystem.Intrusiondetectionsystems(IDS)areusedtomonitorthesystemandnetworktodetectandrespondtosuspiciousbehavior. Therearetwocategoriesofintrusiondetectionmethods:anomalydetectionandsignaturedetection.Anomalydetectionmethodsidentifyactivitiesthatdifferfromnormalbehavior.Signaturedetectionmethodssearchforknownattackpatternsandmatchthemwithobserveddata.Bothmethodsrequiretheuseoffeatureselectiontoselectthemostimportantfeaturesfromthedata.However,selectingthemostimportantfeaturesfromlargeamountsofdataisachallengingtask. Manymethodshavebeenproposedtoselectthemostimportantfeaturesforintrusiondetection.Someofthesemethodsarebasedonthecorrelationcoefficientandinformationgain.However,thesemethodshavetheirlimitations,oftenresultinginahighdimensionalityofthefeaturesetanddecreasedclassificationaccuracy.Toaddressthisissue,thispaperproposesafeatureselectionmethodbasedonparticleswarmoptimization(PSO)andneighborhoodreduction(NR)forintrusiondetectionlogdata. Methodo