Towards Preserving Worker Location Privacy in Spatial Crowdsourcing

Abstract

Spatial Crowdsourcing (SC) nowadays has become a popular research topic studying how to outsource a set of spatial-temporal tasks to workers at specific locations. However, there exists a significant security concern: existing location privacy techniques are not applicable to SC. In this paper, we focus on protecting the worker location privacy against the semi-honest adversaries model while preserving the functionality of SC system. By introducing a semi-honest third party and using additive homomorphic encryption, we present a secure task assignment protocol for SC. More specifically, we propose an efficient protocol to securely compute the worker travel cost and select minimum cost worker in the encrypted domain, which reveals nothing about location privacy. We theoretically analyze that our protocol is secure as all encrypted private data are computationally indistinguishable. Extensive experimental results on real-world and synthetic datasets show that the proposed protocol can protect worker location privacy while keeping high task assignment rate.