Detection of Malware in Large Networks using Deep Auto Encoders
K. Janani, R. Gunasundari · International Journal on Recent and Innovation Trends in Computing and Communication · 2023
Data mining and machine learning have been heavily studied in recent years with the purpose of detecting sophisticated malware. The majority of these approaches rely on architectures that do not involve deeply enough into the learning process, despite the fact that they have yielded excellent results. This is because deep learning is finding increasing application in both business and academia thanks due to its skills in feature learning. In this paper, we develop a Deep Auto Encoder (DAE) based detection mechanism to detect the malwares crawling in the large scale networks. The DAE act as an unsupervised deep learning model that helps in detecting the malwares. The simulation is conducted on two different datasets to test the robustness of the model. The results show that the proposed method has higher rate of accuracy in detecting the attacks than other methods.