Combat Mobile Evasive Malware via Skip-Gram-Based Malware Detection

Abstract

Android malware detection is an important research topic in the security area. There are a variety of existing malware detection models based on static and dynamic malware analysis. However, most of these models are not very successful when it comes to evasive malware detection. In this study, we aimed to create a malware detection model based on a natural language model called skip-gram to detect evasive malware with the highest accuracy rate possible. In order to train and test our proposed model, we used an up-to-date malware dataset called Argus Android Malware Dataset (AMD) since the AMD contains various evasive malware families and detailed information about them. Meanwhile, for the benign samples, we used Comodo Android Benign Dataset. Our proposed model starts with extracting skip-gram-based features from instruction sequences of Android applications. Then it applies several machine learning algorithms to classify samples as benign or malware. We tested our proposed model with two different scenarios. In the first scenario, the random forest-based classifier performed with 95.64% detection accuracy on the entire dataset and 95% detection accuracy against evasive only samples. In the second scenario, we created a test dataset that contained zero-day malware samples only. For the training set, we did not use any sample that belongs to the malware families in the test set. The random forest-based model performed with 37.36% accuracy rate against zero-day malware. In addition, we compared our proposed model’s malware detection performance against several commercial antimalware applications using VirusTotal API. Our model outperformed 7 out of 10 antimalware applications and tied with one of them on the same test scenario.

An Attribute Extraction for Automated Malware Attack Classification and Detection Using Soft Computing Techniques

“…The dividing characteristic with the greatest gain ratio is chosen [ 1 ]. The nonleaf nodes of the produced decision tree are regarded as significant characteristics [ 30 ]. The authors combined decision trees and neural networks, resulting in an increase in classification results.…”

A Systematic Overview of the Machine Learning Methods for Mobile Malware Detection

“…rough this process, it classifies samples and regresses a binary division into classification, continuation, or numerical types. As a result of this study, the DT algorithm was used the fourth most [32,37,39,44,46,47,53,56,58,59,62,64,65,68,71,72,75,76,78,85,86,92,96,98,101,111,[120][121][122][123][124][125][126][127][128][129][130][131][132][133][134].…”

“…e study assessed both the MalGenome and private datasets and identified that the BN and RD scored 99.7% and 93.03%, respectively, for the TPR. Egitmen et al [39] used Android software with artificially generated text to classify modern Android malware, but applied a skip-gram technique configured for NLP to extract useful features. is study also demonstrated that the NLP-based static analysis approach for application source code has promising results.…”

FB2Droid: A Novel Malware Family-Based Bagging Algorithm for Android Malware Detection

“…It turns out that the predictive ability of integrated classifiers is much better than that of individual classifiers in general. In the studies using the ensemble classifier, there are two directions: one is to directly use related ensemble classifiers, such as random forest (RF) [36], gradient boosting decision tree (GBDT) [37], and AdaBoost [38]; the other is to use ensemble methods to combine with single classifiers, such as boosting, bagging, and stacking methods. Yerima and Sezer [39] proposed a detection framework, DroidFusion, based on multilevel classifier fusion.…”