Privacy-preserving collaborative web services QoS prediction via YAO’s garbled circuits and homomorphic encryption

Collaborative Web services QoS prediction has become an important tool for the generation of accurate personalized QoS which is a cornerstone of most QoS-based approaches for Web services selection and composition. While a number of achievements have been attained on the study of improving the accuracy of collaborative QoS prediction, little work has been done for protecting user privacy in this process. In this paper, we propose a privacy-preserving collaborative QoS prediction framework which can protect the private data of users while retaining the ability of generating accurate QoS prediction. We combine Yao’s garbled circuit and additively homomorphic encryption via additively secret sharing to address non-linear computations required in the process of QoS pre- diction. We implement the proposed framework based on FasterGC, an open source implementation of Yao’s garbled circuit, and conduct extensive simulations to study its performance. Simulation results, together with theoretical security and complexity analysis, show that privacy-preserving QoS prediction can be efficiently achieved in our framework.