Practical Differentially Private Modeling of Human Movement Data

Abstract

Exciting advances in big data analysis suggest that sharing personal information, such as health and location data, among multiple other parties could have significant societal benefits. However, privacy issues often hinder data sharing. Recently, differential privacy emerged as an important tool to preserve privacy while sharing privacy-sensitive data. The basic idea is simple. Differential privacy guarantees that results learned from shared data do not change much based on the inclusion or exclusion of any single person's data. Despite the promise, existing differential privacy techniques addresses specific utility goals and/or query types (e.g., count queries), so it is not clear whether they can preserve utility for arbitrary types of queries. To better understand possible utility and privacy tradeoffs using differential privacy, we examined uses of human mobility data in a real-world competition. Participants were asked to come up with insightful ideas that leveraged a minimally protected published dataset. An obvious question is whether contest submissions could yield the same results if performed on a dataset protected by differential privacy? To answer this question, we studied synthetic dataset generation models for human mobility data using differential privacy. We discuss utility evaluation and the generality of the models extensively. Finally, we analyzed whether the proposed differential privacy models could be used in practice by examining contest submissions. Our results indicate that most of the competition submissions could be replicated using differentially private data with nearly the same utility and with privacy guarantees. Statistical comparisons with the original dataset demonstrate that differentially private synthetic versions of human mobility data can be widely applicable for data analysis.

Advances in Crowd Analysis for Urban Applications Through Urban Event Detection

“…For example, the trajectory data provided by CDR tracks individuals and preferences risking their privacy as it is possible to uniquely track 95% of peoples' trajectories by knowing only four spatio-temporal points [139]. Though various methods, e.g., obfuscation [140], k-anonymity [141], differentially private model [71], [142], information fusion and aggregation [143], have been proposed, yet privacy protection remains an open challenge.…”

Collection, usage and privacy of mobility data in the enterprise and public administrations

“…To give a few examples: There are simple approaches like the reduction of granularity of coordinates [20] or reducing the sampling interval [21]. More advanced methods aim to provide indistinguishability between individuals within a dataset, like k-anonymity [22], or provide uninformativeness with the guarantee of differential privacy, e.g., [23][24][25][26].…”

Privacy in trajectory micro-data publishing : a survey

“…A more detailed view of the considered distributions and their combination is in Figure18. The synthetic movement data52 produced by DP-WHERE is proven to preserve population density distributions over time, as well as daily ranges of commutes in the reference area.Roy et al[113] follow a similar approach in their proposed Sanitization Model. First, they remove outlying records from the original dataset by applying the statistical interquartile range rule to all attributes.…”