Fake AP Detection Technology Based on Improved DBSCAN Algorithm

Abstract

AbstractWith the rapid development of the mobile Internet, mobile users’ access to the Internet through wireless networks has become one of the main access methods for obtaining information. However, the openness of wireless networks makes them vulnerable to fake AP attacks. Currently, detection research for such attacks is often based on whitelisting, however it is not always feasible to register device fingerprints in advance in practice. Aiming at such situation, this paper proposes a pseudo AP detection method based on DBSCAN algorithm. Using the nonlinear phase error feature extracted from the channel state information (CSI), the method can cluster the fingerprint data of different devices into different clusters, and then can judge the existence of the fake AP attack behavior. At the same time, this paper improves the algorithm and introduces the K-means nearest neighbor idea into the DBSCAN algorithm, so that the parameters can be adaptively selected according to the characteristics of the sample itself. The experimental results show that the method proposed in this paper can divide different wireless devices, and then can accurately detect the fake AP attack behavior in this scenario.KeywordsWireless networkFake APChannel state informationNonlinear phase errorDBSCAN