隐私计算场景下数据质量治理探索与实践

doi:10.11959/j.issn.2096-0271.2022073

摘要/Abstract

摘要：

隐私计算是一种新型数据处理技术，可以在保护数据隐私及安全的前提下，实现数据价值转化和流通。然而隐私计算场景中“数据可用不可见”的特性给传统的数据质量治理工作带来了很大的挑战，业界尚缺乏完善的解决方案。针对上述问题，提出一种适用于隐私计算场景的数据质量治理方法与流程，构建了本地与多方两个层级的数据质量评估体系，能够兼顾本地域及联邦域的数据质量治理工作，同时提出了一种数据贡献度衡量方法，对隐私计算的长效激励机制进行探索，从而提升隐私计算的数据质量，并提高计算结果的精度。

关键词: 隐私计算, 联邦学习, 数据质量治理, 数据贡献度

Abstract:

Privacy computing is a new data processing technology, which can realize the transformation and circulation of a data value on the premise of protecting data privacy and security.However, the invisible feature of data in private computing scenarios poses a great challenge to traditional data quality management.There is still a lack of perfect solutions.To solve the above problems in the industry, a data quality governance method and process suitable for privacy computing scenarios were proposed.A local and multi-party data quality evaluation system was constructed, which could take into account the data quality governance of the local domain and the federal domain.At the same time, a data contribution measurement method was proposed to explore the long-term incentive mechanism of privacy computing, improve the data quality of privacy computing, and improve the accuracy of computing results.

Key words: privacy computing, federated learning, data quality governance, data contribution

中图分类号:

D922.16，TP18

张燕, 杨一帆, 伊人, 罗圣美, 唐剑飞, 夏正勋. 隐私计算场景下数据质量治理探索与实践[J]. 大数据, 2022, 8(5): 55-73.

Yan ZHANG, Yifan YANG, Ren YI, Shengmei LUO, Jianfei TANG, Zhengxun XIA. Exploration and practice of data quality governance in privacy computing scenarios[J]. Big Data Research, 2022, 8(5): 55-73.

图/表 10

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

参考文献 46

[1]	中国信息通信研究院,隐私计算联盟. 隐私计算白皮书(2021年)[R]. 2021.
	China Academy of Information and Communication Technology,Privacy Computing Alliance. Privacy computing white paper(2021)[R]. 2021.
[2]	符芳诚, 侯忱, 程勇 ,等. 隐私计算关键技术与创新[J]. 信息通信技术与政策, 2021,47(6): 27-37.
	FU F C , HO U C , CHENG Y ,et al. Key technology and innovation of privacy preserving computing[J]. Information and Communications Technology and Policy, 2021,47(6): 27-37.
[3]	HARDY S , HENECKA W , IVEY-LAW H , ,et al. Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption[J]. arXiv preprint,2017,arXiv:1711.10677.
[4]	李凤华, 李晖, 贾焰 ,等. 隐私计算研究范畴及发展趋势[J]. 通信学报, 2016,37(4): 1-11.
	LI F H , LI H , JIA Y ,et al. Privacy computing:concept,connotation and its research trend[J]. Journal on Communications, 2016,37(4): 1-11.
[5]	YANG S W , REN B , ZHOU X H ,et al. Parallel distributed logistic regression for vertical federated learning without thirdparty coordinator[J]. arXiv preprint,2019,arXiv:1911.09824.
[6]	WAND Y , WANG R Y . Anchoring data quality dimensions in ontological foundations[J]. Communications of the ACM, 1996,39(11): 86-95.
[7]	PIPINO L L , LEE Y W , WANG R Y . Data quality assessment[J]. Communications of the ACM, 2002,45(4): 211-218.
[8]	刘金晶, 王梅 . 大数据下的数据质量评价指标构建实践[J]. 计算机技术与发展, 2019,29(10): 46-50.
	LIU J J , WANG M . Practice of data quality evaluating index construction under big data[J]. Computer Technology and Development, 2019,29(10): 46-50.
[9]	中国信息通信研究院,大数据技术标准推进委员会. 数据资产管理实践白皮书(4.0)[S]. 2019.
	China Academy of Information and Communication Technology,Big Data Technology and Standerd Committee. 数据资产管理实践白皮书(4.0)[S]. 2019.
[10]	Firstlogic. Data quality assessment:a methodology for success[Z]. 2003.
[11]	HEER J , HELLERSTEIN J M , KANDEL S . Data wrangling[M]// Encyclopedia of big data technologies. Cham: Springer, 2019: 584-591.
[12]	杨青云, 赵培英, 杨冬青 ,等. 数据质量评估方法研究[J]. 计算机工程与应用, 2004,40(9): 3-4,15.
	YANG Q Y , ZHAO P Y , YANG D Q ,et al. Research on data quality assessment methodology[J]. Computer Engineering and Applications, 2004,40(9): 3-4,15.
[13]	WANG R Y , STOREY V C , FIRTH C P . A framework for analysis of data quality research[J]. IEEE Transactions on Knowledge and Data Engineering, 1995,7(4): 623-640.
[14]	方幼林, 杨冬青, 唐世渭 ,等. 数据仓库中数据质量控制研究[J]. 计算机工程与应用, 2003,39(13): 1-4.
	FANG Y L , YANG D Q , TANG S W ,et al. Data quality managements in data warehouse[J]. Computer Engineering and Applications, 2003,39(13): 1-4.
[15]	包阳, 齐璇, 李海龙 . 大型软件系统数据质量问题研究[J]. 计算机工程与设计, 2011,32(3): 963-967,987.
	BAO Y , QI X , LI H L . Research on data quality of large-scale software system[J]. Computer Engineering and Design, 2011,32(3): 963-967,987.
[16]	宗威, 吴锋 . 大数据时代下数据质量的挑战[J]. 西安交通大学学报(社会科学版), 2013,33(5): 38-43.
	ZONG W , WU F . The challenge of data quality in the big data age[J]. Journal of Xi’an Jiaotong University (Social Sciences), 2013,33(5): 38-43.
[17]	吴信东, 董丙冰, 堵新政 ,等. 数据治理技术[J]. 软件学报, 2019,30(9): 2830-2856.
	WU X D , DONG B B , DU X Z ,et al. Data governance technology[J]. Journal of Software, 2019,30(9): 2830-2856.
[18]	中国信息通信研究院. 数据安全治理实践指南(1.0)[R]. 2001.
	China Academy of Information and Communication Technology. Data security governance practice guide (1.0)[R]. 2001.
[19]	黄刘生, 田苗苗, 黄河 . 大数据隐私保护密码技术研究综述[J]. 软件学报, 2015,26(4): 945-959.
	HUANG L S , TIAN M M , HUANG H . Preserving privacy in big data:a survey from the cryptographic perspective[J]. Journal of Software, 2015,26(4): 945-959.
[20]	彭南博, 王虎 ,等. 联邦学习技术及实战[M]. 北京: 电子工业出版社, 2021.
	PENG N B , WANG H ,et al. Federated learning techniques and practices[M]. Beijing: Publishing House of Electronics Industry, 2021.
[21]	杨强, 刘洋, 程勇 ,等. 联邦学习[M]. 北京: 电子工业出版社, 2020.
	YANG Q , LIU Y , CHENG Y ,et al. Federated learning[M]. Beijing: Publishing House of Electronics Industry, 2020.
[22]	李安然 . 面向特定任务的大规模数据集质量高效评估[D]. 合肥:中国科学技术大学, 2021.
	LI A R . Efficient task-oriented quality assessment for large-scale datasets[D]. Hefei:University of Science and Technology of China, 2021.
[23]	WANG G , DANG C X , ZHOU Z Y . Measure contribution of participants in federated learning[C]// Proceedings of 2019 IEEE International Conference on Big Data. Piscataway:IEEE Press, 2019: 2597-2604.
[24]	朱建明, 张沁楠, 高胜 ,等. 基于区块链的隐私保护可信联邦学习模型[J]. 计算机学报, 2021,44(12): 2464-2484.
	ZHU J M , ZHANG Q N , GAO S ,et al. Privacy preserving and trustworthy federated learning model based on blockchain[J]. Chinese Journal of Computers, 2021,44(12): 2464-2484.
[25]	王鑫, 周泽宝, 余芸 ,等. 一种面向电能量数据的联邦学习可靠性激励机制[J]. 计算机科学, 2022,49(3): 31-38.
	WANG X , ZHOU Z B , YU Y ,et al. Reliable incentive mechanism for federated learning of electric metering data[J]. Computer Science, 2022,49(3): 31-38.
[26]	KONE?NY J , MCMAHAN H B , YU F X ,et al. Federated learning:strategies for improving communication efficiency[J]. arXiv preprint,2016,arXiv:1610.05492.
[27]	LI T , SAHU A K , TALWALKAR A ,et al. Federated learning:challenges,methods,and future directions[J]. arXiv preprint,2019,arXiv:1908.07873.
[28]	YAO A C , . Protocols for secure computations[C]// Proceedings of 23rd Annual Symposium on Foundations of Computer Science. Piscataway:IEEE Press, 1982: 160-164.
[29]	Open Mobile Terminal Platform Consortium. Advanced trusted environment:OMTP TR1[Z]. 2009.
[30]	杨强 . 联邦学习：人工智能的最后一公里[J]. 智能系统学报, 2020,15(1): 183-186.
	YANG Q . Federated learning:the last on kilometer of artificial intelligence[J]. CAAI Transactions on Intelligent Systems, 2020,15(1): 183-186.
[31]	杨一帆, 邵一淼, 施宇 . 一种分位数的获取方法,设备及存储介质:CN202111153418[J].[P]. 2021-09-29.
	YANG Y F , SHAO Y M , SHI Y . A method,device and storage medium for obtaining quantiles:CN202111153418[J].[P]. 2021-09-29.
[32]	CRISTOFARO E , TSUDIK G . Practical private set intersection protocols with linear computational and bandwidth complexity[C]// Proceedings of the 14th International Conference on Financial Cryptography and Data Security. Heidelberg:Springer, 2010: 143-159.
[33]	CRISTOFARO E , TSUDIK G . On the performance of certain private set intersection protocols[C]// Proceedings of the 5th International Conference on Trust ＆Trustworthy Computing.[S.l.:s.n.], 2012.
[34]	FREEDMAN M J , NISSIM K , PINKAS B . Efficient private matching and set intersection[C]// Proceedings of the 2014 International Conference on the Theory and Applications of Cryptographic Techniques. Heidelberg:Springer, 2004: 1-19.
[35]	GOOD I J . Weight of evidence:a brief survey[J]. Bayesian Statistics, 1985(2): 249-270.
[36]	RODRIGUEZ-LUJAN I , HUERTA R , ELKAN C ,et al. Quadratic programming feature selection[J]. The Journal of Machine Learning Research, 2010,11(2): 1491-1516.
[37]	JOHNSON T , DASU T . Data quality and data cleaning[C]// Proceedings of the 2003 ACM SIGMOD International Conference on Management of Data. New York:ACM Press, 2003:681.
[38]	叶焕倬, 吴迪 . 相似重复记录清理方法研究综述[J]. 现代图书情报技术, 2010(9): 56-66.
	YE H Z , WU D . A survey of approximately duplicate data cleaning method[J]. New Technology of Library and Information Service, 2010(9): 56-66.
[39]	朱晓峰 . 缺失值填充的若干问题研究[D]. 桂林:广西师范大学, 2007.
	ZHU X F . Studies on missing data imputation[D]. Guilin:Guangxi Normal University, 2007.
[40]	程开明 . 统计数据预处理的理论与方法述评[J]. 统计与信息论坛, 2007,22(6): 98-103.
	CHENG K M . The theory and methods of data preparation:an overview[J]. Statistics ＆ Information Forum, 2007,22(6): 98-103.
[41]	贾俊平, 何晓群, 金勇进 . 统计学(第六版)[M]. 北京: 中国人民大学出版社, 2015.
	JIA J P , HE X Q , JIN Y J . Statistics[M]. Beijing: China Renmin University Press, 2015.
[42]	LIPOVETSKY S , CONKLIN M . Analysis of regression in game theory approach[J]. Applied Stochastic Models in Business and Industry, 2001,17(4): 319-330.
[43]	?TRUMBELJ E , KONONENKO I . Explaining prediction models and individual predictions with feature contributions[J]. Knowledge and Information Systems, 2014,41(3): 647-665.
[44]	LUNDBERG S , LEE S I . A unified approach to interpreting model predictions[J]. arXiv preprint,2017,arXiv:1705.07874.
[45]	汪云云, 陈松灿 . 基于AUC的分类器评价和设计综述[J]. 模式识别与人工智能, 2011,24(1): 64-71.
	WANG Y Y , CHEN S C . A survey of evaluation and design for AUC based classifier[J]. Pattern Recognition and Artificial Intelligence, 2011,24(1): 64-71.
[46]	张义莲, 颜晟, 朱旻捷 ,等. 机器学习系统毒化攻击综述[J]. 通信技术, 2020,53(3): 535-542.
	ZHANG Y L , YAN S , ZHU M J ,et al. Overview on poisoning attacks against machine learning system[J]. Communications Technology, 2020,53(3): 535-542.