Statistical analytics on encrypted data requires a fully-homomorphic encryption (FHE) scheme. However, heavy computation overheads make FHE impractical. In this paper we propose a novel approach to achieve privacy-preserving statistical analysis on an encrypted database. The main idea of this work is to construct a privacy-preserving calculator to calculate attributes’ count values for later statistical analysis. To authenticate these encrypted count values, we adopt an authenticable additive homomorphic encryption scheme to construct the calculator. We formalize the notion of an authenticable privacy-preserving calculator that has properties of broadcasting and additive homomorphism. Further, we propose a cryptosystem based on binary vectors to achieve complex logic expressions for statistical analysis on encrypted data. With the aid of the proposed cryptographic calculator, we design several protocols for statistical analysis including conjunctive, disjunctive and complex logic expressions to achieve more complicated statistical functionalities. Experimental results show that the proposed scheme is feasible and practical.

中文翻译：

---

对云端加密数据的可验证数据分析

对加密数据的统计分析需要全同态加密 (FHE) 方案。然而，繁重的计算开销使得 FHE 不切实际。在本文中，我们提出了一种新方法来实现对加密数据库的隐私保护统计分析。这项工作的主要思想是构建一个隐私保护计算器来计算属性的计数值，以便以后进行统计分析。为了验证这些加密的计数值，我们采用可验证的加性同态加密方案来构造计算器。我们将具有广播和加性同态属性的可验证隐私保护计算器的概念形式化。此外，我们提出了一种基于二进制向量的密码系统，以实现对加密数据进行统计分析的复杂逻辑表达式。借助所提出的密码计算器，我们设计了多种统计分析协议，包括合取、析取和复杂逻辑表达式，以实现更复杂的统计功能。实验结果表明，所提出的方案是可行和实用的。