Open AccessMalware Detection Using a Machine-Learning Based Approach
Author(s) -
Safa Rkhouya,
Khalid Chougdali
Publication year - 2021
Publication title -
international journal of information technology and applied sciences
Language(s) - English
Resource type - Journals
ISSN - 2709-2208
DOI - 10.52502/ijitas.v3i4.172
Subject(s) - false positive paradox , malware , computer science , gradient boosting , decision tree , machine learning , artificial intelligence , random forest , support vector machine , boosting (machine learning) , false positive rate , true positive rate , false positives and false negatives , data mining , computer security
The purpose of this research work is to study the usage of machine learning in detecting malware. This paper presents a versatile framework, in which a dataset of more than 130000 files has been analyzed, to train and test four machine learning algorithms: Support Vector Machine, Decision Tree, Random Forest, and Gradient Boosting; The performance of each algorithm in malware classification, has been studied based on the: Accuracy, execution time, rate of false positives and false negatives, and area under the Receiver Operating Characteristic curve.