Title: Malware algorithm classification method based on big data analysis

Authors: Jingling Zhao; Shilei Chen; Mengchen Cao; Baojiang Cui

Addresses: National Engineering Laboratory for Mobile Network Security, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China ' National Engineering Laboratory for Mobile Network Security, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China ' National Engineering Laboratory for Mobile Network Security, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China ' National Engineering Laboratory for Mobile Network Security, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China

Abstract: Internet technology has greatly increased the number of malware attacks on networks. Consequently, it has also elevated the importance of automatic malware detection and classification technology based on big data analysis in the field of information security. This paper presents a new method for classifying malware algorithms that exhibits both high accuracy and high coverage. The method combines big data analysis with software security technologies such as feature extraction, machine learning, binary instrumentation and dynamic instruction flow analysis to achieve automated classification of malware algorithms. 20 classification experiments prove the correctness of the method. We also discuss future directions for improving the method.

Keywords: malware analysis; malware classification; big data analytics; feature extraction; machine learning; binary instrumentation; dynamic instruction flow; malware attacks; network security; malware detection; information security; malware algorithms.

DOI: 10.1504/IJWGS.2017.082077

International Journal of Web and Grid Services, 2017 Vol.13 No.1, pp.112 - 130

Received: 16 Mar 2016
Accepted: 05 Aug 2016

Published online: 06 Feb 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article