Improving the detection accuracy of unknown malware by partitioning the executables in groups

TL;DR

This paper proposes a novel approach to improve unknown malware detection accuracy by partitioning executables based on file size, achieving approximately 8.7% better accuracy than traditional methods.

Contribution

The study introduces a dataset partitioning technique based on file size for feature selection, enhancing malware detection accuracy over conventional methods.

Findings

Partitioning by file size improves detection accuracy by ~8.7%.

Feature selection based on size ranges outperforms all-in-one dataset approaches.

The method demonstrates significant gains in identifying unknown malware.

Abstract

Detection of unknown malware with high accuracy is always a challenging task. Therefore, in this paper, we study the classification of unknown malware by two methods. In the first/regular method, similar to other authors [17][16][20] approaches we select the features by taking all dataset in one group and in the second method, we select the features by partitioning the dataset in the range of file 5 KB size. We find that the second method to detect the malware with ~8.7% more accurate than the first/regular method.