Show simple item record

dc.contributor.authorGhinita, Gabriel
dc.contributor.authorKalnis, Panos
dc.contributor.authorKantarcioǧlu, Murât
dc.contributor.authorBertino, Elisa
dc.date.accessioned2015-08-04T06:20:03Z
dc.date.available2015-08-04T06:20:03Z
dc.date.issued2009
dc.identifier.citationGhinita, G., Kalnis, P., Kantarcioglu, M., & Bertino, E. (2009). A Hybrid Technique for Private Location-Based Queries with Database Protection. Lecture Notes in Computer Science, 98–116. doi:10.1007/978-3-642-02982-0_9
dc.identifier.isbn3642029817; 9783642029813
dc.identifier.issn03029743
dc.identifier.doi10.1007/978-3-642-02982-0_9
dc.identifier.urihttp://hdl.handle.net/10754/564234
dc.description.abstractMobile devices with global positioning capabilities allow users to retrieve points of interest (POI) in their proximity. To protect user privacy, it is important not to disclose exact user coordinates to un-trusted entities that provide location-based services. Currently, there are two main approaches to protect the location privacy of users: (i) hiding locations inside cloaking regions (CRs) and (ii) encrypting location data using private information retrieval (PIR) protocols. Previous work focused on finding good trade-offs between privacy and performance of user protection techniques, but disregarded the important issue of protecting the POI dataset D. For instance, location cloaking requires large-sized CRs, leading to excessive disclosure of POIs (O(|D|) in the worst case). PIR, on the other hand, reduces this bound to , but at the expense of high processing and communication overhead. We propose a hybrid, two-step approach to private location-based queries, which provides protection for both the users and the database. In the first step, user locations are generalized to coarse-grained CRs which provide strong privacy. Next, a PIR protocol is applied with respect to the obtained query CR. To protect excessive disclosure of POI locations, we devise a cryptographic protocol that privately evaluates whether a point is enclosed inside a rectangular region. We also introduce an algorithm to efficiently support PIR on dynamic POI sub-sets. Our method discloses O(1) POI, orders of magnitude fewer than CR- or PIR-based techniques. Experimental results show that the hybrid approach is scalable in practice, and clearly outperforms the pure-PIR approach in terms of computational and communication overhead. © 2009 Springer Berlin Heidelberg.
dc.publisherSpringer Nature
dc.titleA hybrid technique for private location-based queries with database protection
dc.typeConference Paper
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentOffice of the VP
dc.identifier.journalAdvances in Spatial and Temporal Databases
dc.conference.date8 July 2009 through 10 July 2009
dc.conference.name11th International Symposium on Spatial and Temporal Databases, SSTD 2009
dc.conference.locationAalborg
dc.contributor.institutionPurdue University, West Lafayette, IN 47907, United States
dc.contributor.institutionUniversity of Texas at Dallas, Richardson, TX 75080, United States
kaust.personKalnis, Panos


This item appears in the following Collection(s)

Show simple item record