Insider Threat Detection Using Supervised Machine Learning Algorithms on an Extremely Imbalanced Dataset

Naghmeh Moradpoor Sheykhkanloo, A. Hall
{"title":"Insider Threat Detection Using Supervised Machine Learning Algorithms on an Extremely Imbalanced Dataset","authors":"Naghmeh Moradpoor Sheykhkanloo, A. Hall","doi":"10.4018/ijcwt.2020040101","DOIUrl":null,"url":null,"abstract":"An insider threat can take on many forms and fall under different categories. This includes malicious insider, careless/unaware/uneducated/naïve employee, and the third-party contractor. Machine learning techniques have been studied in published literature as a promising solution for such threats. However, they can be biased and/or inaccurate when the associated dataset is hugely imbalanced. Therefore, this article addresses the insider threat detection on an extremely imbalanced dataset which includes employing a popular balancing technique known as spread subsample. The results show that although balancing the dataset using this technique did not improve performance metrics, it did improve the time taken to build the model and the time taken to test the model. Additionally, the authors realised that running the chosen classifiers with parameters other than the default ones has an impact on both balanced and imbalanced scenarios, but the impact is significantly stronger when using the imbalanced dataset.","PeriodicalId":41462,"journal":{"name":"International Journal of Cyber Warfare and Terrorism","volume":"61 s81","pages":"1-26"},"PeriodicalIF":0.2000,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.4018/ijcwt.2020040101","citationCount":"20","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Cyber Warfare and Terrorism","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4018/ijcwt.2020040101","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"POLITICAL SCIENCE","Score":null,"Total":0}
引用次数: 20

Abstract

An insider threat can take on many forms and fall under different categories. This includes malicious insider, careless/unaware/uneducated/naïve employee, and the third-party contractor. Machine learning techniques have been studied in published literature as a promising solution for such threats. However, they can be biased and/or inaccurate when the associated dataset is hugely imbalanced. Therefore, this article addresses the insider threat detection on an extremely imbalanced dataset which includes employing a popular balancing technique known as spread subsample. The results show that although balancing the dataset using this technique did not improve performance metrics, it did improve the time taken to build the model and the time taken to test the model. Additionally, the authors realised that running the chosen classifiers with parameters other than the default ones has an impact on both balanced and imbalanced scenarios, but the impact is significantly stronger when using the imbalanced dataset.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
在极不平衡数据集上使用监督机器学习算法进行内部威胁检测
内部威胁可以采取多种形式,并属于不同的类别。这包括恶意的内部人员,粗心/不知情/未受教育/naïve员工和第三方承包商。在已发表的文献中,机器学习技术已经被研究为解决此类威胁的有希望的解决方案。然而,当相关的数据集非常不平衡时,它们可能是有偏见和/或不准确的。因此,本文将在极不平衡的数据集上解决内部威胁检测问题,其中包括采用一种称为扩展子样本的流行平衡技术。结果表明,尽管使用这种技术平衡数据集并没有提高性能指标,但它确实改善了构建模型和测试模型所花费的时间。此外,作者意识到,使用默认参数以外的参数运行所选分类器对平衡和不平衡场景都有影响,但当使用不平衡数据集时,影响明显更强。
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 去求助
来源期刊
CiteScore
1.80
自引率
40.00%
发文量
20
期刊最新文献
Meta-Analysis and the Integration of Terrorism Event Databases Modeling and Simulating Student Protests Through Agent-Based Framework Artificial Intelligence and Facial Recognition in an IoT Ecosystem IoT and Edge Computing as Enabling Technologies of Human Factors Monitoring in CBRN Environment Integrated Information Model of an Enterprise and Cybersecurity Management System: From Data to Activity
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1