Estimating Software Obfuscation Potency with Artificial Neural Networks

CANAVESE, DANIELE;REGANO, LEONARDO;BASILE, CATALDO;VITICCHIE', ALESSIO

2017-01-01

---

Abstract

This paper presents an approach to estimate the potency of obfuscation techniques. Our approach uses neural networks to accurately predict the value of complexity metrics – which are used to compute the potency – after an obfuscation transformation is applied to a code region. This work is the first step towards a decision support to optimally protect software applications.