Differentially private counting of users’ spatial regions

Abstract

Mining of spatial data is an enabling technology for mobile services, Internetconnected cars, and the Internet of Things. But the very distinctiveness of spatial data that drives utility, can cost user privacy. Past work has focused upon points and trajectories for differentially-private release. In this work, we continue the tradition of privacy-preserving spatial analytics, focusing not on point or path data, but on planar spatial regions. Such data represents the area of a user's most frequent visitation-such as "around home and nearby shops". Specifically we consider the differentially-private release of data structures that support range queries for counting users' spatial regions. Counting planar regions leads to unique challenges not faced in existing work. A user's spatial region that straddles multiple data structure cells can lead to duplicate counting at query time. We provably avoid this pitfall by leveraging the Euler characteristic for the first time with differential privacy. To address the increased sensitivity of range queries to spatial region data, we calibrate privacy-preserving noise using bounded user region size and a constrained inference that uses robust least absolute deviations. Our novel constrained inference reduces noise and promotes covertness by (privately) imposing consistency. We provide a full end-to-end theoretical analysis of both differential privacy and high-probability utility for our approach using concentration bounds. A comprehensive experimental study on several real-world datasets establishes practical validity.

On-the-Fly Privacy for Location Histograms

“…In that research, however, the whole histogram is known to the protection algorithm and it is processed/obfuscated in one go, not on the fly as in our approach. We refer the interested reader to Fanaeepour and Rubinstein [24] for a very recent effort on protecting a histogram in one go.…”

Spatial Statistic Data Release Based on Differential Privacy

“…In recent years, the privacy preserving of data releasing has received considerable attention. Researchers have proposed some influential release methods based on differential privacy [9][10][11][12][13][14]16,[19][20][21][22][23]. We briefly review the relevant work here and discuss the differences between our work and existing work.…”

“…The rest of the researchers [14,19,20] have studied hybrid partitions or other conditions. The DPCube [14] algorithm proposed by Xiao has two steps.…”

“…A new metric is proposed to determine whether the nodes that will minimize the non-uniformity error are close to uniform. Maryam [19] provided a method that focuses on counting planar spatial regions where the users visited most frequently. They leveraged the Euler characteristic with differential privacy for the first time to address the problem of duplicate counting when a planar body spaned multiple grid cells, and a novel constrained inference uses the least absolute deviations to increase the utility of the data.…”

Locally differentially private continuous location sharing with randomized response

“…There are a large number of works adopting differential privacy to location privacy preservation. 1,10 Most of them, for example, Al-Hussaeni et al, 11 Qardaji et al, 12 and Fanaeepour and Rubinstein, 13 have applied the traditional differential privacy (or centralized differential privacy, CDP) 9 on location or trace data for data publishing or aggregation with a trusted server. As privacy matters are raised frequently, local differential privacy (LDP) 14 has been considered in many application fields due to its more stringent and practical privacy.…”