Facial reconstruction

Search LJMU Research Online

Browse Repository | Browse E-Theses

Behaviour-aware Malware Classification: Dynamic Feature Selection

Dinh Vu, P, Shone, N, Phan Huy, D, Shi, Q, Nguyen Viet, H and Tran Nguyen, N Behaviour-aware Malware Classification: Dynamic Feature Selection. In: IEEE Explore . (11th International Conference on Knowledge and Systems Engineering (KSE), 24 October 2019 - 26 October 2019, Da Namg, Vietnam). (Accepted)

[img]
Preview
Text
PID6113979.pdf - Accepted Version

Download (278kB) | Preview

Abstract

Despite the continued advancements in security research, malware persists as being a major threat in this digital age. Malware detection is a primary defence strategy for most networks but the identification of malware strains is becoming increasingly difficult. Reliable identification is based upon characteristic features being detectable within an object. However, the limitations and expense of current malware feature extraction methods is significantly hindering this process. In this paper, we present a new method for identifying malware based on behavioural feature extraction. Our proposed method has been evaluated using seven classification methods whilst analysing 2,068 malware samples from eight different families. The results achieved thus far have demonstrated promising improvements over existing approaches.

Item Type: Conference or Workshop Item (Paper)
Additional Information: © 2019 IEEE.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
Divisions: Computer Science
Publisher: IEEE
Date Deposited: 22 Nov 2019 10:01
Last Modified: 22 Nov 2019 10:01
URI: http://researchonline.ljmu.ac.uk/id/eprint/11669

Actions (login required)

View Item View Item