Privacy-Preserving Location Information Fusion for Secure Localization in Cyber–Physical Social Systems: A Case of Consumer’s Trustworthy Personalized Recommendation

Cyber-physical social systems (CPSS) have developed significantly in the last decade as a result of their effective computing and communication capabilities. Security and safety concerns, yet continue to be the biggest obstacle to the wider acceptance of CPSS in spite of all technological developments. In this work, we investigate the problem of secure localization of roaming users along with preserving their privacy in CPSS through location information fusion. We present a novel idea of privacy preserving location information fusion based on linear combination aggregation and extend it for its use in CPSS ensuring the privacy of anchor’s locations and dimensions, and target’s location while roaming in CPSS environment. Furthermore, a privacy-preserving secure localization scheme is offered, together with the necessary cryptographic support to ensure the ultimate aim of privacy. In CPSS contexts where real-time location information is crucial for participant’s safety, the proposed privacy-preserving secure localization scheme can be implemented. The proposed scheme is assessed through the implementation of a trustworthy personalized consumer recommendation system. The experimental results demonstrate that the proposed method can guarantee high recommendation accuracy and achieve the accuracy and diversity of personalized recommendations under varying recommendation list lengths when compared to other reliable methods for personalized consumer recommendations.