Convolutional neural network based evil twin attack detection in WiFi networks

Evil Twin Attack (ETA) refers to attackers use a device impersonate legitimate hotspot. To address the problem of ETAs in WiFi network, Convolutional Neural Network (CNN) attack detection method is proposed. The uses preamble signal as feature and it train CNN based classification model. Next, trained model detect potential ETA by inconsistent identity claims feature. Experiments on commercial hardware demonstrate that proposed can effectively Attack.