Malware detection in windows using deep learning classification approach / Aishah Anuar and Mohd Faris Mohd Fuzi

Cybercrime has become a major threat to every individual, business, and national security system in the modern world. Deep learning has been implemented in numerous safety-focused environments for the purpose of protecting applications as a result of its rapid evolution and notable success in a wide range of applications. Due to the precision of the data and the capacity to train a huge number of data, deep learning has become popular in response to the current high demand. In terms of accomplishing the project's objective, the project's success was determined by its outputs. Using the Metric Formula Definition Accuracy, the performance of CNN and RNN malware detection models in Windows has been tested. According to the afore mentioned models, CNN is doing better, providing an accuracy of 97.5 percent in detecting malware, whereas RNN provides an accuracy of 88.5 percent and respectively. This study evaluated the performance accuracy between the CNN and RNN architecture models.