Gauss-Mapping Black Widow Optimization with Deep Extreme Learning Machine for Android Malware Classification Model

Nowadays, the malware on Android platform is found to be increasing. With prevalent use of code obfuscation technology, precision antivirus software and classical detection techniques low. Classical signature matching manual analysis have exposed issues like low accuracy slow speed. Several authors overcome issue utilizing machine learning (ML) had more research outcomes. growth deep (DL), many researchers started DL methods for detecting malware. This article introduces a Gauss-Mapping Black Widow Optimization with Deep Learning Enabled Malware Classification (GBWODL-AMC) model. The major intention GBWODL-AMC technique lies in automated classification To accomplish this, involves design GBWO based feature selection approach enhance performance. For purposes, employs extreme (DELM) model its parameter are optimally selected by ant lion optimization (ALO) algorithm. simulation tested CICAndMal2017 dataset. Extensive experimental results signify better performance over other detectors maximum 98.95%.