Secure and efficient publicly verifiable outsourcing of matrix multiplication in online mode

Abstract

With the emergence of cloud computing paradigm in many scientific applications, outsourcing of computation has attracted a great amount of attention from the research community. Outsourcing of heavy computations such as multiplication of two large matrices has raised some security concerns. Data and the result of computation should be protected not only from attackers, but also from the cloud servers. Moreover, data owner should be able to verify the correctness of computation with complexity less than the original computation. The previous schemes either have expensive offline phase or do not support public verifiability. In this paper, first we find a security vulnerability in the Zhang-Lei’s scheme for outsourcing of matrix multiplication where the cloud server can forge the result and pass the verification phase. Then, we present a secure and efficient publicly verifiable outsourcing of matrix multiplication scheme which achieves privacy protection of outsourced data and result, unforgeability of result, public verifiability and high efficiency. Our analyses show that compared with the related work, the proposed scheme is superior in terms of functionality, computation, communication and storage overhead, especially in verification computation overhead. © 2020, Springer Science+Business Media, LLC, part of Springer Nature.