Study on the Different Types of Neural Networks to Improve the Classification of Ransomwares

Among the diversity of malware, we mention “Ransomware”. Its main objective is to take a user’s data hostage, preventing and blocking access to the data and even to the computer (depending on the type of attack). The data is released once the ransom is paid. Despite the efforts of developers and the research community, this scourge remains a viable security threat that is why there is competition between IT community (developers and researchers) to realize and create a tool and method to detect malware, among the methods and techniques used are Artificial Intelligence and more precisely machine learning using neural networks. In this paper, we will discuss the different types of neural networks, the related work of each type, aiming at the classification of malware in general and ransomware in particular. After this study, we will talk about the methodology followed for the implementation of our neural network model (multilayer perceptron). We tested this model, firstly, with the binary classification if it is a malware or a goodware, and secondly, with the classification of the nine families of Ransomware by taking the vector of our previous work and we will make a comparison on the accuracy rate of the instance that are correctly classified.