Dear all,

We are submitting a paper “Ensemble Based Classification using Neural Networks and Machine Learning Models for Windows PE Malware Detection” to the journal Electronics MDPI. The paper’s abstract is below. If accepted we will acknowledge SPARTA.

The authors are Robertas Damaševičius, Algimantas Venčkauskas, Jevgenijus Toldinas, Šarūnas Grigaliūnas.

All the best,

Algimantas Venčkauskas

______________________________________________________

Abstract: Security of information is one of the greatest challenges facing organizations and institutions. Cybercrime is rising in frequency and magnitude in recent years with new ways to steal, change, destroy information or disable the information system appearing every day. One of the types of penetration into the information system where confidential information is processed is malware. An attacker injects malware into a computer system, after which he has full or partial access to critical information in the information system. This paper proposes an ensemble classification-based methodology for malware detection. The first-stage classification is performed by a stacked ensemble of dense (fully connected) and convolutional neural networks (CNN), while the final stage classification is performed by a meta-learner. For a meta-learner, we explored and compared 14 classifiers. For a baseline comparison, 13 machine learning methods are used: K-Nearest Neighbors, Linear Support Vector Machine (SVM), RBF SVM, Random Forest, AdaBoost, Decision Tree, ExtraTrees, Linear Discriminant Analysis, Logistic, Neural Net, Passive Classifier, Ridge Classifier, and Stochastic Gradient Descent classifier. We present the results of experiments performed on the Classification of Malware with PE headers (ClaMP) dataset. The best performance was achieved by an ensemble of five dense and CNN neural networks, and the ExtraTrees classifier as a meta-learner.