支持浮点运算的高效并行全同态加密算法

摘要

The rapid development of cloud computing provide convenience to people,as well as security problems,such as privacy preserving.One of the major ways to solve this problem is to utilize fully homomorphic encryption(FHE) algorithm to support operations on the encrypted data directly.However,because most fully homomorphic encryption schemes only support limited data types for the time being,it is difficult to apply them to reality.In this paper,a fully homomorphic encryption algorithm supporting floating-point operations and a parallelization algorithm based on Spark were proposed.The security and performance of the parallel algorithm were analyzed in theory and experiments were conducted to demonstrate its practical performance.Experimental results show that the overall speed-up ratio of the given algorithm can reach 3.9 in a 4-node 16-core cluster and the encryption time and calculation time on encrypted data can be reduced effectively.The parallel fully homomorphic encryption algorithm can satisfy the encryption requirement of large-scale data in cloud environment.%云计算的快速发展在给人们带来便利的同时,其隐私安全问题也备受关注.结合全同态加密算法,实现直接对密文的运算,是解决隐私安全问题的一种可行方案.但目前大多同态算法支持的数据类型有限,难以有效应用于实际环境.鉴于此,提出一种支持浮点运算的全同态加密算法,以及基于Spark环境的并行算法,并分析了算法的安全性和实际性能.实验结果表明,基于Spark的并行浮点数全同态加密算法支持整数和浮点同态运算,在4节点16核心的集群中能够达到3.9的整体加速比,能有效减少数据加密和密文运算的时间,满足云计算环境中对大规模浮点数据进行高效同态加密的需求.