Implementation of CNN-MLP and CNN-LSTM for MitM Attack Detection System

Man in the Middle (MitM) is one of attack techniques conducted for eavesdropping on data transitions or conversations between users some systems secretly. It has a sizeable impact because it could make attackers will do another attack, such as website system deface phishing. Deep Learning be able to predict various well. Hence, this study, we would like present approach detect MitM attacks and process its data, by implementing hybrid deep learning methods. We used 2 (two) combinations methods, which are CNN-MLP CNN-LSTM. also Feature Scaling methods before building model determine better detecting well feature selection that generate highest accuracy. Kitsune Network Attack Dataset (ARP Ettercap) dataset study. The results prove than CNN-LSTM average, accuracy rate respectively at 99.74%, 99.67%, 99.57%, using Standard Scaler (99.74%) among other scenarios.