Detection And Classificaiton Of Malware Using Progressive Principal Component And Attension Based Deep Neural Network
Detecting the malware with required match oncollected network anomaly detection datasets is becoming a large-scale identification problem due to the upcoming of novel malware alternatives. As it quickly and precisely recognizesthe new malware attacks, it permits security analysts to acknowledge in an efficient manner. Traditional malware detection methods are specifically concentrated on cost effectiveness and detection accuracy. They had the drawback of not being able to detect in the computation oriented manner and classification them according to types of attacks. To address these issues, malware detection and classification using Progressive Principal Component and Attentionbased Deep Neural Network (PPC-ADNN) is presented. The PPC-ADNN method involves two steps namely, attack detection and attack classification. First, Progressive Balanced Principal Component Analysis model is designed to obtain computationally efficient network features and then to detect the attacks accordingly by means of Progressive Ratio Variance. Next, Attentionbased Deep Neural Network Attack Classification model is presented to determine the types of attacks by utilizing attention weight factor. The considerable experimental results illustrate the usefulness of the proposed method in terms of attack detection time, attack detection overhead and classification accuracy.