可信区块链隐私计算平台研究与实现  

Research and Implementation of Trusted Blockchain Privacy Computing Platform

作　　者：胡绍洲 马兆丰 叶可可 HU Shaozhou;MA Zhaofeng;YE Keke(School of Cyberspace Security,Beijing University of Posts and Telecommunications,Beijing 100876,China;China Mobile Information Technology Co.,Ltd.,Beijing 102200,China)

机构地区：[1]北京邮电大学网络空间安全学院,北京100876 [2]中移动信息技术有限公司研发创新中心,北京102200

出　　处：《信息安全与通信保密》2022年第10期1-11,共11页Information Security and Communications Privacy

基　　金：北京市自然科学基金项目(No.M21034);国家重点研发计划项目(No.2020YFB1005500)。

摘　　要：区块链系统的共识机制和密码学机制保障了链上信息的真实性和流通性,但同时其无法解决链上信息的隐私保护问题,对于需要隐私保护的数据源缺少隐私保护的功能。隐私计算技术往往采用中心化方案,但难以保证数据在传入和传出可信执行环境前未被篡改,导致多方数据可信协同难以实现。在电子拍卖机制场景下,基于联盟链技术和隐私计算机制设计可信区块链隐私计算平台,采用同态加密方案Paillier算法以及联盟链技术,并对两种主流同态加密方案Paillier和CKKS进行性能测试。通过同态加密方案,在不透露数据源的具体数值的情况下实现数据源正确性计算证明,该平台能够有效实现隐私数据安全计算。The consensus mechanism and cryptography mechanism of the blockchain system ensure the authenticity and circulation of information on the chain,but at the same time,it cannot solve the problem of information privacy protection on the chain,and lacks the function of privacy protection for data sources that require privacy protection. Privacy computing technology often adopts centralized solutions that make it difficult to ensure that data is not tampered with before it is passed in and out of the trusted execution environment,which makes multi-party data trusted collaboration difficult to achieve. In the scenario based on electronic auction mechanism,this paper designs a trusted blockchain privacy computing platform based on consortium chain technology and privacy computing mechanism,adopting the homomorphic encryption scheme Paillier algorithm implementation as well as alliance chain technology,and conducts performance tests on two main stream homomorphic encryption schemes,Paillier and CKKS. Through the homomorphic encryption scheme,the data source correctness calculation proof is realized without revealing the specific value of the data source,and the platform can effectively realize the secure calculation of private data.

关 键 词：隐私计算 同态加密 联盟链 智能合约 电子拍卖 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]