全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

改进贝叶斯算法在未知恶意软件识别中的研究

Keywords: 分类器,数据挖掘,贝叶斯算法

Full-Text   Cite this paper   Add to My Lib

Abstract:

为改进朴素贝叶斯(naiveBayes,NB)算法在识别未知恶意代码过程中学习速度慢的缺点,在分析研究朴素贝叶斯算法、复合贝叶斯(multi-naiveBayes,MNB)算法的基础上,提出了一种改进贝叶斯(half-incrementnaiveBayes,HNB)算法.算法采用特征集增量学习方式,在保证分类精度不降低的前提下,学习速度提高约30%.实际样本测试表明,分类精度达到了96%,其中对已知恶意代码的分类精度达到99%.

References

[1]  MCGRAW G,MORRISETTG.Attacking malicious code:a report to the infosec research council[J].IEEE Software,2000,17(5):33-41.
[2]  COHEN F.Computer viruses—theory and experiments[J].Computers and Security,1987,6(1):22-35.
[3]  SPINELLIS D.Reliable identification of bounded-length viruses is NP complete[J].IEEE Transactions on InformationTheory,2003,49(1):280-284.
[4]  KEPHART J O,SORKIN G B,ARNOLD W C,et al.Biologically inspired defenses against computer viruses[C]∥Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence.San Fransisco:Publisher of MorganKaufmann,1995:985-996.
[5]  TESAURO G J,KEPHARTJ O,SORKIN G B.Neural networks for computer virus recognition[J].IEEE Expert,1996,11(4):5-6.
[6]  LEE W,STOLFO S J,MOK K W.A data mining framework for building intrusion detection models[C]∥Bob Wener.Proceedings of the 1999 IEEE Symposium on Security and Privacy.North Kansas:Technical Communication Services,1999:120-132.
[7]  LEE W,STOLFO S J,CHAN P K.Learning patterns from UNIX processes execution traces for intrusion detection[R]∥AAAI Workshop on AI Approaches to Fraud Detection and Risk Management.California:AAAI Press,1997:50-56.
[8]  SCHULTZ M G,ESKIN E,ZADOK E,et al.Data mining methods for detection of new malicious executables[C]∥FrancesM Titsworth.Proceedings of 2001 IEEE Symposium on Security and Privacy.Florida:The Printing House,2001:38-49.
[9]  KOLTER J Z,MALOOF M A.Learning to detect and classify malicious executables in the wild[J].Journal of MachineLearning Research,2006(7):2721-2744.
[10]  ZHANG Bo-yun,YIN Jian-ping,HAO Jing-bo.Intelligent detection computer viruses based on multiple classifiers[C]∥Ubiquitous Intelligence and Computing.Heidelberg:Springer Berlin,2007:1181-1190.
[11]  ZHANG Bo-yun,YINJian-ping,HAO Jing-bo.Using fuzzy pattern recognition to detect unknown malicious executables code[C]∥Fuzzy Systems and Knowledge Discovery.Heidelberg:Springer Berlin,2005:629-634.
[12]  张波云,殷建平,张鼎兴,等.基于K-最近邻算法的未知病素检测[J].计算机工程与应用,2005(6):7-10.ZHANG Bo-yun,YIN Jian-ping,ZHANG Ding-xing,et al.Unknown computer virus detection based onK-nearest neighboralgorithm[J].Computer Engineering and Applications,2005(6):7-10.(in Chinese)
[13]  宫秀军,刘少辉,史忠植.一种增量贝叶斯分类模型[J].计算机学报,2002,25(6):645-650.GONG Xiu-jun,LIU Shao-hui,SHI Zhong-zhi.An incremental Bayes classification model[J].Chinese Journal ofComputers,2002,25(6):645-650.(in Chinese)
[14]  HENCHIRI O,JAPKOWICZ N.A feature selection and evaluation scheme for computer virus detecting[C]∥Proceedings ofthe 6th International Conference on Data Mining(ICDM’06).Hong kong:ACM Press,2006:1-6.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133