SECRECSY: A Secure Framework for Enhanced Privacy-Preserving Location Recommendations in Cloud Environment

Abstract

The development of Recommender Systems (RSs) aims to generate recommendations with high quality, and on the other hand, the privacy of the user is not considered as a significant issue. Especially, when the RS utilizes the cloud platform for the recommendation generation process, the privacy of the user is needed to be preserved to ensure the security of user’s sensitive data. In this paper, we present an Improved MORE approach as a Fully Homomorphic Encryption algorithm to secure user’s data in the cloud environment. To generate secure location recommendations to the users, we present SECure RECommendation SYstem (SECRECSY) framework by protecting user’s sensitive privacy information in the cloud during the recommendation generation process. To meet the increasing demands of group recommendations, we extend our SECRECSY as Group Recommendation Model to suggest POIs to the group of users. The experimental results and findings are helpful to the researchers for developing better RSs for both individual and group users.