Location-Visiting Characteristics Based Privacy Protection of Sensitive Relationships

Abstract

In the era of Internet of Things (IoT), the problem of the privacy leakage of sensitive relationships is critical. This problem is caused by the spatial–temporal correlation between users in location-based social networks (LBSNs). To solve this problem, a sensitive relationship-protection algorithm based on location-visiting characteristics is proposed in this paper. Firstly, a new model based on location-visiting characteristics is proposed for calculating the similarity between users, which evaluates check-in features of users and locations. In order to avoid an adversary inferring sensitive relationship privacy and to ensure the utility of data, our proposed algorithm adopts a heuristic rule to evaluate the impact of deduction contributions and information loss caused by data modifications. In addition, location-search technology is proposed to improve the algorithm’s execution efficiency. The experimental results show that our proposed algorithm can effectively protect the privacy of sensitive data.