Wasserstein Metric-Based Location Spoofing Attack Detection in WiFi Positioning Systems

• Main Authors: Yinghua Tian, Nae Zheng, Xiang Chen, Liuyang Gao
• Format: Article
• Language: English
• Published: Hindawi-Wiley 2021-01-01
• Series: Security and Communication Networks
• Online Access: http://dx.doi.org/10.1155/2021/8817569

WiFi positioning systems (WPS) have been introduced as parts of 5G location services (LCS) to provide fast positioning results of user devices in urban areas. However, they are prominently threatened by location spoofing attacks. To end this, we present a Wasserstein metric-based attack detection scheme to counter the location spoofing attacks in the WPS. The Wasserstein metric is used to measure the similarity of each two hotspots by their signal’s frequency offset distribution features. Then, we apply the clustering method to find the fake hotspots which are generated by the same device. When applied with WPS, the proposed method can prevent location spoofing by filtering out the fake hotspots set by attackers. We set up experimental tests by commercial WiFi devices, which show that our method can detect fake devices with 99% accuracy. Finally, the real-world test shows our method can effectively secure the positioning results against location spoofing attacks.