协同优化决策中数据水平分区的隐私保护算法研究  

Privacy-Preserving Algorithm Research on Horizontally Partitioned Data of Collaborative Optimization Decisions

作　　者：刘智慧[1] 刘洪伟[1] 詹明君[1] 肖祺[1] 陈晓旋[1] 

机构地区：[1]广东工业大学管理学院,广东广州510520

出　　处：《广东工业大学学报》2016年第5期15-21,共7页Journal of Guangdong University of Technology

基　　金：国家自然科学基金资助项目(70971027);广东省普通高校人文社会科学重点研究项目(12ZS0112)

摘　　要：在跨组织协同优化决策问题中的参数来源于不同主体的数据.在缺乏可信第三方时难以完成全局优化问题的求解.本文运用随机矩阵转换和加密技术方法来解决约束条件中数据水平分区优化问题的协同计算,克服了扰动或差分算法对问题结构以及解结构潜在的不稳定影响.提出的安全协议一方面可以保证在保护各方隐私信息的前提下得到计算结果与集中式的结果具有一致性,另一方面也具备良好的防推理攻击能力.该研究可广泛应用于供应链系统或企业联盟间的决策优化问题的协同安全计算问题.In the cross-organizational collaborative optimal decision-making, the parameters of optimiza-tion usually originate from different subject data. It is difficult to solve the global optimization problems due to the lack of a trusted third party. A method combining the random matrix transformation and en-cryption technology is put forward to solve the collaborative optimization of the horizontally partitioned da-ta. This method also overcomes the potential destabilizing impact of structural problems and structural so-lutions when using disturbance or difference algorithm. On one hand, the security protocol can ensure the consistency of calculation results with privacy-preserving and centralized results. On the other side, it can prevent the potential inference attack. The study can be widely used in collaborative computing security issues of optimization decision problems among enterprise alliance or supply chain.

关 键 词：数据水平分区 安全协议 推理攻击 

分 类 号：TP309.2[自动化与计算机技术—计算机系统结构]