Robust Malware Family Classification Using Effective Features and Classifiers

• Main Authors: Hammad B.T., Jamil N., Ahmed I.T., Zain Z.M., Basheer S.
• Other Authors: 57193327622
• Format: Article
• Published: MDPI 2023

Malware development has significantly increased recently, posing a serious security risk to both consumers and businesses. Malware developers continually find new ways to circumvent security research�s ongoing efforts to guard against malware attacks. Malware Classification (MC) entails labeling a class of malware to a specific sample, while malware detection merely entails finding malware without identifying which kind of malware it is. There are two main reasons why the most popular MC techniques have a low classification rate. First, Finding and developing accurate features requires highly specialized domain expertise. Second, a data imbalance that makes it challenging to classify and correctly identify malware. Furthermore, the proposed malware classification (MC) method consists of the following five steps: (i) Dataset preparation: 2D malware images are created from the malware binary files; (ii) Visualized Malware Pre-processing: the visual malware images need to be scaled to fit the CNN model�s input size; (iii) Feature extraction: both hand-engineering (Tamura) and deep learning (GoogLeNet) techniques are used to extract the features in this step; (iv) Classification: to perform malware classification, we employed k-Nearest Neighbor (KNN), Support Vector Machines (SVM), and Extreme Learning Machine (ELM). The proposed method is tested on a standard Malimg unbalanced dataset. The accuracy rate of the proposed method was extremely high, making it the most efficient option available. The proposed method�s accuracy rate was outperformed both the Hand-crafted feature and Deep Feature techniques, at 95.42 and 96.84 percent. � 2022 by the authors.