Cluster-oriented ensemble classifiers for intelligent malware detection

With explosive growth of malware and due to its damage to computer security, malware detection is one of the cyber security topics that are of great interests. Many research efforts have been conducted on developing intelligent malware detection systems applying data mining techniques. Such techniqu...

Full description

Saved in:

Bibliographic Details
Published in:	Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015) pp. 189 - 196
Main Authors:	Shifu Hou, Lifei Chen, Tas, Egemen, Demihovskiy, Igor, Yanfang Ye
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01-02-2015
Subjects:	Training
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	With explosive growth of malware and due to its damage to computer security, malware detection is one of the cyber security topics that are of great interests. Many research efforts have been conducted on developing intelligent malware detection systems applying data mining techniques. Such techniques have successes in clustering or classifying particular sets of malware samples, but they have limitations that leave a large room for improvement. Specifically, based on the analysis of the file contents extracted from the file samples, existing researches apply only specific clustering or classification methods, but not integrate them together. Actually, the learning of class boundaries for malware detection between overlapping class patterns is a difficult problem. In this paper, resting on the analysis of Windows Application Programming Interface (API) calls extracted from the file samples, we develop the intelligent malware detection system using cluster-oriented ensemble classifiers. To the best of our knowledge, this is the first work of applying such method for malware detection. A comprehensive experimental study on a real and large data collection from Comodo Cloud Security Center is performed to compare various malware detection approaches. Promising experimental results demonstrate that the accuracy and efficiency of our proposed method outperform other alternate data mining based detection techniques.
DOI:	10.1109/ICOSC.2015.7050805