Optimized Feature Selection and classification for Non-Portable Executable Malware

Abstract

Malware is a program that executes harmful acts and steals information. nowadays it is widely recognized as oneof the largest hazards. In this research work machine learning is used to identify and detect Non-PE file features. The variousdistinct aspects of the Non-PE files features can correlate with one another, being clean or affected, led to the identification ofsuch features. by using machine learning algorithms such as Ada Boost Classifier,Gaussian NB, KNClassifier,RF Classifier, SGD classifier, and feature selection produced the best detection rate also Prediction accuracy of thealgorithms is used to compare the efficacy and efficiency.