Using Approximation of Standard Deviation and Variance in Flow Features for Efficient Intrusion Detection

Dora Pušelj, Lovro Katić, Dominik Ostroski, Ivona Brajdic, Karlo Slovenec
{"title":"Using Approximation of Standard Deviation and Variance in Flow Features for Efficient Intrusion Detection","authors":"Dora Pušelj, Lovro Katić, Dominik Ostroski, Ivona Brajdic, Karlo Slovenec","doi":"10.23919/ConTEL52528.2021.9495962","DOIUrl":null,"url":null,"abstract":"Intrusion Detection Systems (IDS) are one of the most important defense tools against dangerous and sophisticated network attacks. In recent years high-speed network interfaces have become common in data centers and servers. To process such high-speed network traffic entirely, the feature extraction phase of an IDS must be highly efficient. The speed and overall efficiency of the feature extraction phase of anomaly-based Intrusion Detection Systems can be improved by substituting the exact values for standard deviation and variance with lower complexity approximations. This paper demonstrates that using range rule of thumb approximations instead of exact values does not affect the classification results of the model tested in its various configurations. The results show that the accuracy of the model output obtained using the approximations does not differ from the results obtained using the real values by more than 0.05%.","PeriodicalId":269755,"journal":{"name":"2021 16th International Conference on Telecommunications (ConTEL)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 16th International Conference on Telecommunications (ConTEL)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.23919/ConTEL52528.2021.9495962","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Intrusion Detection Systems (IDS) are one of the most important defense tools against dangerous and sophisticated network attacks. In recent years high-speed network interfaces have become common in data centers and servers. To process such high-speed network traffic entirely, the feature extraction phase of an IDS must be highly efficient. The speed and overall efficiency of the feature extraction phase of anomaly-based Intrusion Detection Systems can be improved by substituting the exact values for standard deviation and variance with lower complexity approximations. This paper demonstrates that using range rule of thumb approximations instead of exact values does not affect the classification results of the model tested in its various configurations. The results show that the accuracy of the model output obtained using the approximations does not differ from the results obtained using the real values by more than 0.05%.
基于流特征标准差和方差近似的高效入侵检测
入侵检测系统(IDS)是抵御危险和复杂网络攻击的最重要的防御工具之一。近年来,高速网络接口在数据中心和服务器中变得越来越普遍。为了完全处理如此高速的网络流量,IDS的特征提取阶段必须非常高效。用复杂度较低的近似代替标准差和方差的精确值,可以提高基于异常的入侵检测系统特征提取阶段的速度和整体效率。本文证明,使用范围经验法则近似代替精确值并不影响模型在各种配置下测试的分类结果。结果表明,使用近似方法得到的模型输出精度与使用实际值得到的结果相差不超过0.05%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信