一种基于差分隐私的集值型数据发布方法  

A Privacy-Preserving Method for Set-Valued Data Releasing Based on Differential Privacy

作　　者：王天放 张龙军[2] 陈晓 

机构地区：[1]武警工程大学研究生管理大队,陕西西安710086 [2]武警工程大学信息工程系,陕西西安710086

出　　处：《武警工程大学学报》2015年第6期52-56,共5页Journal of Engineering University of the Chinese People＇s Armed Police Force

摘　　要：随着数据发布和分析等应用需求的出现与发展，如何保护隐私数据和防止敏感信息泄露成为当前信息安全领域的一个研究热点。差分隐私近年来受到了极大关注并被广泛研究。针对集值型数据隐私保护发布的数据安全性和效用性不足，提出了一种基于差分隐私的集值型数据发布方法SDRM。该方法利用前缀树重构数据集，采用压缩感知技术对重构后的数据进行压缩并恢复，并在此过程中对数据进行隐私保护处理，最终发布符合隐私约束的数据集。实验结果表明，该方法能为数据的发布提供有效的隐私保护，并保证了数据的效用性。As the emergence and development of application requirements such as data analysis and data publication, how to protect private data and prevent sensitive information from disclosing is becoming a hot topic in the information security field currently. As a new privacy notion. differential privacy （DP）has grown in popularity recently due to its rigid and provable privacy guarantee. This paper introduces the basic concept and implementation method about differential privacy and proposes a differential private set-valued data releasing method to solve the problem that most existing methods and privacy models cannot accommodate both utility and privacy security of the data. A prefix tree is built to reconstruct the dataset, and the Compressive Sensing is used for compression to the data. During the process the data has been remolded by differential privacy method, and then the final data are released. Experimental results demonstrate that the SDRM can preserve privacy of the sensitive data well ,meanwhile maintain better data utility.

关 键 词：集值型数据 差分隐私 压缩感知 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]