对KDD CUP 99数据集的详细分析

2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications Pub Date : 2009-07-08 DOI:10.1109/CISDA.2009.5356528

Mahbod Tavallaee, E. Bagheri, Wei Lu, A. Ghorbani

{"title":"对KDD CUP 99数据集的详细分析","authors":"Mahbod Tavallaee, E. Bagheri, Wei Lu, A. Ghorbani","doi":"10.1109/CISDA.2009.5356528","DOIUrl":null,"url":null,"abstract":"During the last decade, anomaly detection has attracted the attention of many researchers to overcome the weakness of signature-based IDSs in detecting novel attacks, and KDDCUP'99 is the mostly widely used data set for the evaluation of these systems. Having conducted a statistical analysis on this data set, we found two important issues which highly affects the performance of evaluated systems, and results in a very poor evaluation of anomaly detection approaches. To solve these issues, we have proposed a new data set, NSL-KDD, which consists of selected records of the complete KDD data set and does not suffer from any of mentioned shortcomings.","PeriodicalId":6407,"journal":{"name":"2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications","volume":"28 1","pages":"1-6"},"PeriodicalIF":0.0000,"publicationDate":"2009-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3487","resultStr":"{\"title\":\"A detailed analysis of the KDD CUP 99 data set\",\"authors\":\"Mahbod Tavallaee, E. Bagheri, Wei Lu, A. Ghorbani\",\"doi\":\"10.1109/CISDA.2009.5356528\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"During the last decade, anomaly detection has attracted the attention of many researchers to overcome the weakness of signature-based IDSs in detecting novel attacks, and KDDCUP'99 is the mostly widely used data set for the evaluation of these systems. Having conducted a statistical analysis on this data set, we found two important issues which highly affects the performance of evaluated systems, and results in a very poor evaluation of anomaly detection approaches. To solve these issues, we have proposed a new data set, NSL-KDD, which consists of selected records of the complete KDD data set and does not suffer from any of mentioned shortcomings.\",\"PeriodicalId\":6407,\"journal\":{\"name\":\"2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications\",\"volume\":\"28 1\",\"pages\":\"1-6\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2009-07-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3487\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CISDA.2009.5356528\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CISDA.2009.5356528","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 3487

摘要

在过去的十年中，异常检测已经引起了许多研究人员的关注，以克服基于签名的入侵防御系统在检测新型攻击方面的弱点，而KDDCUP'99是最广泛使用的用于评估这些系统的数据集。在对该数据集进行统计分析后，我们发现了两个重要的问题，这些问题严重影响了评估系统的性能，并导致对异常检测方法的评估非常差。为了解决这些问题，我们提出了一个新的数据集，NSL-KDD，它由完整的KDD数据集的选定记录组成，并且没有上述任何缺点。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A detailed analysis of the KDD CUP 99 data set

During the last decade, anomaly detection has attracted the attention of many researchers to overcome the weakness of signature-based IDSs in detecting novel attacks, and KDDCUP'99 is the mostly widely used data set for the evaluation of these systems. Having conducted a statistical analysis on this data set, we found two important issues which highly affects the performance of evaluated systems, and results in a very poor evaluation of anomaly detection approaches. To solve these issues, we have proposed a new data set, NSL-KDD, which consists of selected records of the complete KDD data set and does not suffer from any of mentioned shortcomings.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications

自引率

0.00%

发文量