Skip to main navigation Skip to search Skip to main content

Malware detection based on objective-oriented association mining

  • Xiao Xiao
  • , Ding Yuxin
  • , Zhang Yibin
  • , Tang Ke
  • , Dai Wei
  • Harbin Institute of Technology Shenzhen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Signature matching methods are inadequate to detect unseen malwares. In this paper an API (Application Programming Interface) based data mining method is proposed to detect unseen malwares. The data mining algorithm, objective-oriented associate mining (OOA), is employed to mine association rules for detecting malwares. To find association rules with strong discrimination power, an improved algorithm for frequent item generation is presented. In this algorithm a frequent item is evaluated by its support and its classification capability. The experiments prove that the proposed methods are effective and can be used to detect malware variants and unknown malicious executable.

Original languageEnglish
Title of host publicationProceedings - International Conference on Machine Learning and Cybernetics
PublisherIEEE Computer Society
Pages375-380
Number of pages6
ISBN (Electronic)9781479902576
DOIs
StatePublished - 2013
Externally publishedYes
Event12th International Conference on Machine Learning and Cybernetics, ICMLC 2013 - Tianjin, China
Duration: 14 Jul 201317 Jul 2013

Publication series

NameProceedings - International Conference on Machine Learning and Cybernetics
Volume1
ISSN (Print)2160-133X
ISSN (Electronic)2160-1348

Conference

Conference12th International Conference on Machine Learning and Cybernetics, ICMLC 2013
Country/TerritoryChina
CityTianjin
Period14/07/1317/07/13

Keywords

  • Classification
  • Machine learning
  • Malware detection
  • Objective-oriented associate mining
  • Security
  • Tracking

Fingerprint

Dive into the research topics of 'Malware detection based on objective-oriented association mining'. Together they form a unique fingerprint.

Cite this