Malware Detection in AdHoc E-Government Network Using Machine Learning

Malware developers have been kept tremendously busy in recent years due to the increasing use of the Android operating system in e-government operations. Significant numbers of virus developers have as their primary purpose the transformation of mobile devices into bots. As a result, it is now feasible for hackers to take control of the device and maybe other devices that are connected to it, so forming botnets. Botnets are utilized to aid the execution of numerous harmful operations, including distributed denial of service (DDoS), spamming, and data theft, among others. The aim of this research was to determine whether an unidentified application is a “attack” or a “normal” application by gleaning static and dynamic information from it. Some examples include the k-nearest neighbors (KNN) [17], the support vector machine (SVM) [18], the convolutional neural networks (CNN) [19], the dense neural networks (DNN) [20], the gated recurrent units (GRU), the long short-term memory (LSTM) [21], and the hybrid deep learning convolutional neural networks long/short-term memory (CNN-LSTM) and convolutional neural networks [22], [23]. It was assessed how effective various machine learning and deep learning algorithms are at detecting mobile malware attacks, and a number of these techniques were evaluated.