Hide me Behind the Noise: Local Differential Privacy for Indoor Location Privacy

TL;DR

This paper introduces a privacy-preserving framework using Local Differential Privacy for indoor location data, ensuring user privacy while maintaining accurate population zone frequencies in indoor environments.

Contribution

It presents a novel LDP-based framework for indoor location privacy that is practically feasible and effective, verified on real-world datasets.

Findings

Framework effectively protects user location privacy.

Population zone frequency accuracy remains high.

Framework's performance depends on dataset properties and privacy levels.

Abstract

The advent of numerous indoor location-based services (LBSs) and the widespread use of many types of mobile devices in indoor environments have resulted in generating a massive amount of people's location data. While geo-spatial data contains sensitive information about personal activities, collecting it in its raw form may lead to the leak of personal information relating to the people, violating their privacy. This paper proposes a novel privacy-aware framework for aggregating the indoor location data employing the Local Differential Privacy (LDP) technique, in which the user location data is changed locally in the user's device and is sent to the aggregator afterward. Therefore, the users' locations are kept hidden from a server or any attackers. The practical feasibility of applying the proposed framework is verified by two real-world datasets. The impact of dataset properties, the privacy mechanisms, and the privacy level on our framework are also investigated. The experimental results indicate that the presented framework can protect the location information of users, and the accuracy of the population frequency of different zones in the indoor area is close to that of the original population frequency with no knowledge about the location of people indoors.