Location Prediction of Rogue Access Point Based on Deep Neural Network Approach

Abstract

One of the serious security problems in wireless local networks (WLAN) is the existence of the rogue access points (RAPs). To prevent our network from the RAP attacks, we need to identify the RAPs by using the RAP detection methods. However, the identification of RAP location is also a challenging task. The objective of this paper is to propose the location prediction scheme for the RAP. We call our proposed scheme as the location prediction of rogue access point (LPRAP). The LPRAP scheme consists of two mechanisms, the RAP detection mechanism and the RAP location prediction mechanism. We apply the concept of the fingerprint in the RAP detection mechanism by considering the SSID, time duration of broadcasting beacon frame and MAC address. We show that this mechanism can detect the number of RAP. For the RAP location prediction mechanism, we utilize the deep neuron network (DNN) to predict the location of RAPs and evaluate its effectiveness. We evaluate the performance of LPRAP by comparing with those of other machine learning methods such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naive Bayes, and Multi-layer Perceptron (MLP). We also compare with particle swarm optimization algorithm. The results show that LPRAP can accurately predict the location of RAP up to 99.29%.