AMVG: Adaptive Malware Variant Generation Framework Using Machine Learning

摘要: There are advances in detecting malware using machine learning (ML), but it is still a challenging task to detect advanced variants (e.g., polymorphic and metamorphic variations). To such variants, we first need understand the methods used generate them bypass detection methods. In this paper, introduce an adaptive variant generation (AMVG) framework study bypassing efficiently. The AMVG uses ML genetic algorithm (GA)) that satisfy specific criteria. use of GA automates generations with appropriate modules handle various input formats. For experiment, samples retrieved from theZoo, collection samples. results show can automatically varying criteria practical amount time, as well showing capabilities different