通信学报 ›› 2021, Vol. 42 ›› Issue (5): 137-148.doi: 10.11959/j.issn.1000-436x.2021089

• 学术论文 • 上一篇    

基于BCP的联合委托学习模型及协议

高胜1,2, 向康1,3, 田有亮1,3, 谭伟杰1, 冯涛4, 吴晓雪5   

  1. 1 贵州大学计算机科学与技术学院公共大数据国家重点实验室,贵州 贵阳 550025
    2 中央财经大学信息学院,北京 100081
    3 贵州大学密码学与数据安全研究所,贵州 贵阳 550025
    4 兰州理工大学计算机与通信学院,甘肃 兰州 730050
    5 贵州省计量测试院,贵州 贵阳 550000
  • 修回日期:2021-03-26 出版日期:2021-05-01 发布日期:2021-05-01
  • 作者简介:高胜(1987- ),男,湖北黄冈人,博士,中央财经大学副教授、硕士生导师,主要研究方向为数据安全与隐私保护、区块链技术及应用等
    向康(1993- ),男,湖北仙桃人,贵州大学硕士生,主要研究方向为委托机器学习、委托计算与博弈论
    田有亮(1982- ),男,贵州六盘水人,博士,贵州大学教授、博士生导师,主要研究方向为算法博弈论、密码学与安全协议、大数据安全与隐私保护等
    谭伟杰(1981- ),男,陕西合阳人,博士,贵州大学讲师,主要研究方向为通信信号处理、通信网络安全、阵列信号处理
    冯涛(1970- ),男,甘肃临洮人,博士,兰州理工大学研究员、博士生导师,主要研究方向为网络与信息安全、密码学
    吴晓雪(1977- ),男,江苏南通人,贵州省计量测试院工程师,主要研究方向为能源计量
  • 基金资助:
    国家自然科学基金资助项目(61662009);国家自然科学基金资助项目(61772008);国家自然科学基金资助项目(U1836205);国家自然科学基金资助项目(62072487);贵州省科技重大专项计划基金资助项目(20183001);贵州省科技计划基金资助项目([2019]1098);贵州省科技计划基金资助项目([2019]5703);贵州省高层次创新型人才基金资助项目([2020]6008);贵州大学引进人才科研基金资助项目([2020]61);贵州大学培育基金资助项目([2019]56)

BCP-based joint delegation learning model and protocol

Sheng GAO1,2, Kang XIANG1,3, Youliang TIAN1,3, Weijie TAN1, Tao FENG4, Xiaoxue WU5   

  1. 1 State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China
    2 School of Information, Central University of Finance and Economics, Beijing 100081, China
    3 Institute of Cryptography and Data Security, Guizhou University, Guiyang 550025, China
    4 School of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, China
    5 Institute for Metrology and Calibration of Guizhou, Guiyang 550000, China
  • Revised:2021-03-26 Online:2021-05-01 Published:2021-05-01
  • Supported by:
    The National Natural Science Foundation of China(61662009);The National Natural Science Foundation of China(61772008);The National Natural Science Foundation of China(U1836205);The National Natural Science Foundation of China(62072487);Science and Technology Major Support Program of Guizhou Province(20183001);Science and Technology Program of Guizhou Province([2019]1098);Science and Technology Program of Guizhou Province([2019]5703);Project of High-level Innovative Talents of Guizhou Province([2020]6008);Research Project of Guizhou University for Talent Introduction([2020]61);Cultivation Project of Guizhou University([2019]56)

摘要:

为了实现数据安全共享的同时减少客户端在数据挖掘过程中的计算成本,基于 BCP 同态加密算法提出了联合委托学习模型及协议。首先,针对决策树模型的安全构造提出了基于虚假记录的隐私保护方法。其次,根据数据垂直分布与水平分布的情况,基于隐私保护委托点积算法和隐私保护委托求熵算法提出了相应的委托学习协议。最后,给出了委托学习协议及决策树模型结构的安全性证明和性能分析。结果表明,基于虚假记录的隐私保护方法不会影响最终模型的构建,并且各客户端最终获得的模型与真实数据构建的模型具有一致性。

关键词: 委托学习, 决策树, BCP同态加密, 数据挖掘

Abstract:

In order to realize data security sharing and reduce the computing costs of clients in data mining process, a joint delegation learning model and protocol based on BCP homomorphic encryption algorithm was proposed.Firstly, a privacy preserving method based on false records was proposed for the security of decision tree model.Secondly, in view of the vertical and horizontal distribution of data, the corresponding delegation learning protocols based on privacy preserving delegation dot product algorithm and privacy preserving delegation entropy algorithm was proposed.Finally, the security proof and the performance analysis of delegation learning protocols and decision tree model structure were given.The results show that the privacy protection method based on false records does not affect the final model construction, and the final model obtained by each client is the same as that constructed by real data.

Key words: delegation learning, decision tree, BCP homomorphic encryption, data mining

中图分类号: 

No Suggested Reading articles found!