基于Gauss迭代法的线性方程组隐私保护外包计算

Privacy Protection Outsourcing Computing of Linear System of Equations Based on Gauss Iterative Method

云计算是一种能为弱计算设备用户提供外包计算服务的新兴技术,为普通用户节省大量的计算资源。在外包计算中,科学计算是一类重要的应用,尤其以线性方程组外包求解为基本构造块。然而,在将方程组系数和常数项外包给云的过程中,不可避免的涉及隐私泄漏。该文给出具有隐私保护的基于Gauss迭代法的线性方程组外包计算算法,与已有文献中的基于Jacobi迭代的方法相比,在相同精度下,能获得更快的计算速度,从而节省通信资源和计算资源。

Cloud computing is an emerging technology that can provide outsourcing computing services for users with weak computing devices,saving a lot of computing resources for ordinary users.In outsourcing computing,scientific computing is a kind of important application,especially taking the outsourcing solution of linear system of equations as the basic building block.However,in the process of outsourcing equation set coefficients and constant terms to the cloud,privacy leakage is inevitably involved.For this reason,outsourcing computing algorithm of linear system of equations based on Gauss iterative method,with privacy protection is proposed.Compared with the algorithm based on Jacobi iterative in existing literature,the algorithm proposed in this paper has high computing speed under the same precision,so as to save communication resources and computing resources.