A Feature Extraction Method of Hybrid Gram for Malicious Behavior Based on Machine Learning

Abstract

With explosive growth of malware, Internet users face enormous threats from Cyberspace, known as “fifth dimensional space.” Meanwhile, the continuous sophisticated metamorphism of malware such as polymorphism and obfuscation makes it more difficult to detect malicious behavior. In the paper, based on the dynamic feature analysis of malware, a novel feature extraction method of hybrid gram (H-gram) with cross entropy of continuous overlapping subsequences is proposed, which implements semantic segmentation of a sequence of API calls or instructions. The experimental results show the H-gram method can distinguish malicious behaviors and is more effective than the fixed-length n-gram in all four performance indexes of the classification algorithms such as ID3, Random Forest, AdboostM1, and Bagging.