基于局部差分隐私的物联网敏感数据泄露控制  

Leak Control of Sensitive Data in Internet of Things Based on Local Differential Privacy

作　　者：朱丹红[1] 程烨[1] ZHU Dan-hong;CHENG Ye(College of Mathematics and Computer Science,Fuzhou University,Fuzhou Fujian 350108,China)

机构地区：[1]福州大学数学与计算机科学学院,福建福州350108

出　　处：《计算机仿真》2021年第2期472-476,共5页Computer Simulation

基　　金：福建省自然科学基金项目(2018J01796);教育部科技发展中心高校产学研创新基金项目(2018A01020)。

摘　　要：为了有效提高物联网数据安全性,提高敏感数据加密保护范围,提出基于局部差分隐私的物联网敏感数据泄露控制方法。对物联网数据链进行简化,估计数据链距离,设计基于链距离估计的物联网数据挖掘方法。将挖掘到的物联网数据转化为文档,对文档中数据分词部分进行处理,建立规范化的检索格式,构建敏感数据检索序列对数据库中的数据进行检索,得到物联网敏感数据集。以物联网敏感数据集为基础,通过数据初始化、基于局部差分隐私的数据扰动、明文加密、私钥生成、解密等多个步骤实现物联网隐私数据泄露控制。实验结果表明,研究方法的物联网敏感数据检索查全率与查准率较高,具有较高的数据加密覆盖度与风险访问事件定位精度。In order to effectively improve the data security of the Internet of things and the scope of encryption and protection of sensitive data,this article puts forward a method to control the leakage of sensitive data in the Internet of things based on local differential privacy.Firstly,we simplified the data chain of the Internet of things,and estimated the distance of data chain.Based on the estimation of chain distance,we designed the data mining method and then,transformed the data mined from the Internet of things into some documents.After that,we processed the data and words segmentation in documents,and established the standardized retrieval format.Moreover,we constructed the sensitive data retrieval sequence to retrieve the data in database and thus to get the sensitive data set.Based on the sensitive data set of the Internet of things,we achieved the IoT privacy data leakage control through data initialization,data disturbance based on local differential privacy,plaintext encryption,private key generation,and decryption.Experimental results show that the method has high recall rate and precision rate of IoT sensitive data retrieval,high data encryption coverage and high location accuracy for risk access.

关 键 词：局部差分隐私 物联网 敏感数据 泄露控制 链距离估计 检索序列 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]