<![CDATA[Malware is software created to exploit or attack computer systems. Some of the consequences caused by malware such as data leakage, data destruction, and unauthorized access that harm application users. Random Forest as a classification method has been tested in several previous studies, this method is able to produce good performance with high accuracy. This method is also included in the ensemble method that uses a collection of decision trees so that it is able to classify APKs into several classes. Classification is carried out using static features, namely permissions, API Calls, and intent features that will be extracted to characterize each different APK. The dataset in this study consists of a virusshare dataset with a total data of 13,076 APKs. The framework includes pre-processing of datasets, classification method using the Random Forest algorithm, and APK test of the obtained model. In this study, the Synthetic Minority Over-Sampling Technique (SMOTE) was applied to solve the class imbalance problem in the dataset. Based on the results of the research, the best accuracy is obtained in the SMOTE combination of 92.26% and can classify APKs containing malware into 13 types of malware classes.]]>
Copyrights © 2023
