Madani Houria, Ouerdi Noura, Boumesaoud Ahmed, Azizi Abdelmalek
Faculty of Sciences, Mohammed First University, Oujda, Morocco.
Sci Rep. 2022 Mar 19;12(1):4770. doi: 10.1038/s41598-022-08504-6.
Malware threat the security of computers and Internet. Among the diversity of malware, we have "ransomware". Its main objective is to prevent and block access to user data and computers in exchange for a ransom, once paid, the data will be liberated. Researchers and developers are rushing to find reliable and safe techniques and methods to detect Ransomware to protect the Internet user from such threats. Among the techniques generally used to detect malware are machine learning techniques. 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 adopted methodology for the implementation of our neural network model (multilayer perceptron). We tested this model, firstly, with the binary detection whether it is malware or 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 of the accuracy rate of the instances that are correctly classified.
恶意软件威胁计算机和互联网的安全。在恶意软件的多样性中，有一种“勒索软件”。它的主要目的是阻止用户访问数据和计算机，并以此索要赎金，一旦支付赎金，数据将被解锁。研究人员和开发人员正急于寻找可靠且安全的技术和方法来检测勒索软件，以保护互联网用户免受此类威胁。通常用于检测恶意软件的技术之一是机器学习技术。在本文中，我们将讨论不同类型的神经网络及其相关工作，旨在对一般恶意软件尤其是勒索软件进行分类。在这项研究之后，我们将讨论实施我们的神经网络模型（多层感知器）所采用的方法。我们首先使用该模型进行二进制检测，判断其是恶意软件还是良性软件，其次，通过采用我们之前工作的向量对九种勒索软件家族进行分类，并对正确分类实例的准确率进行比较。
