“When and Where Do You Want to Hide?” – Recommendation of Location Privacy Preferences with Local Differential Privacy

Abstract

In recent years, it has become easy to obtain location information quite precisely. However, the acquisition of such information has risks such as individual identification and leakage of sensitive information, so it is necessary to protect the privacy of location information. For this purpose, people should know their location privacy preferences, that is, whether or not he/she can release location information at each place and time. However, it is not easy for each user to make such decisions and it is troublesome to set the privacy preference at each time. Therefore, we propose a method to recommend location privacy preferences for decision making. Comparing to existing method, our method can improve the accuracy of recommendation by using matrix factorization and preserve privacy strictly by local differential privacy, whereas the existing method does not achieve formal privacy guarantee. In addition, we found the best granularity of a location privacy preference, that is, how to express the information in location privacy protection. To evaluate and verify the utility of our method, we have integrated two existing datasets to create a rich information in term of user number. From the results of the evaluation using this dataset, we confirmed that our method can predict location privacy preferences accurately and that it provides a suitable method to define the location privacy preference.

A Comprehensive Survey on Local Differential Privacy

“…Recently, Shin et al [136] developed a novel matrix factorization algorithm under LDP to enhance privacy by guaranteeing individual privacy and completely protecting items and ratings. Similarly, Asada et al [137] applied the locally differentially private matrix factorization method proposed by Shin [136] to location privacy preference recommendation. In addition, Zhou et al [138] proposed a randomized-response-based private recommendation system with high performance and less time and space while locally differentially privacy-preserving individuals' items and ratings.…”

Protecting Spatiotemporal Event Privacy in Continuous Location-Based Services

“…The user may specify one or multiple events that need to be protected. In practice, we can also have default that are suggested by a privacy preference recommendation system for users' selection [14] or pre-specified event templates that are given by the user.…”

“…for spatiotemporal event privacy using Lemma 3.1 to compute Pr(EVENT) and Lemmas 3.2, 3.3 to compute Pr(o1, o2, · · · , oT , EVENT). We note that our approach of computing the joint probability of an event is able to deal with different emission matrices at each t. Sincep o t is a vector of emission probabilities given the observation o t , i.e, a column in the emission matrix, andp D o t is a diagonal matrix whose diagonal elements arep o t , we only need to obtainp o t and p D o t from the corresponding emission matrix at t, and then use suchp D o t in Equations (13) and (14).…”

Successive Point-of-Interest Recommendation With Local Differential Privacy

“…In short, these works focused on decreasing the RMSE during the learning process and attempted to predict users' preferences using explicit feedback that has a fixed scale rating. Some works adopted LDP for building recommendation systems [37], [44], [45]. Guo et al [37] proposed a privacy-preserving item-based CF technique under LDP.…”

“…However, employing only the similarity score between items had a limit to predict the preferences of users on POIs. Asada et al [44] proposed a location preference recommendation system with LDP. However, the location preference here indicated whether a user wants to publish information about a specific location or not, which is a different area from recommending the next POI.…”