Defending Malicious Check-in Based on Access Point Selection for Indoor Positioning System

WiFi fingerprint-based positioning system emerges to offer fundamental location information for indoor mobile users. It facilitates the check-in to point of interest (POI) through submitting received signal strength (RSS) fingerprints in order to evaluate the crowd traffic. However, the crowd traffic evaluation with RSS fingerprints is vulnerable to the malicious check-in attacks. Attackers who are not at the target POI may still submit the self-modified RSS fingerprints located at the target POI in order to illegally increase its crowd traffic and eventually profit from this fake information. In this paper, we propose a defense scheme against malicious check-in based on access point (AP) selection to significantly reduce the success rate of fingerprint modification from attackers. Specifically, we first exploit fingerprint distance between POIs for AP selection. Then, we explore the mutual information between different POI classes to select APs with high robustness. In addition, the level set method (LSM) is developed to search the optimal modified fingerprint to assess attacker's costs. The extensive simulation results show that the proposed scheme can effectively resist attackers with high accuracy and facilitate crowd traffic evaluation of target POI according to the submitted RSS fingerprints.