面向医疗数据发布的动态更新隐私保护算法  

Privacy Preserving Algorithm Based on Dynamic Update in Medical Data Publishing

作　　者：陈虹云 王杰华[1] 胡兆鹏 贾露 喻纪文 CHEN Hong-yun;WANG Jie-hua;HU Zhao-peng;JIA Lu;YU Ji-wen(College of Computer Science and Technology,Nantong University,Nantong,Jiangsu 226019,China)

机构地区：[1]南通大学计算机科学与技术学院,江苏南通226019

出　　处：《计算机科学》2019年第1期206-211,共6页Computer Science

基　　金：国家自然科学基金项目(61170171);江苏高校优势学科建设工程资助项目;江苏省"六大人才高峰"项目(2010-WLW-006);南通市应用基础研究计划项目(GY12016015;MS12016048)资助

摘　　要：随着信息技术的发展,医疗数据发布中的隐私保护技术一直是数据隐私研究的热点,医疗数据发布的同步更新是其中一个重要问题。为解决医疗数据匿名发布的同步问题,提出了一种建立在(α,k)-匿名数据基础上的支持数据动态更新的算法——(α,k)-UPDATE。该算法通过对语义贴近度的计算,在(α,k)-匿名数据集中选择最贴近的等价类,再进行相应的更新操作。更新后的匿名数据集满足(α,k)-匿名约束,可有效地保护患者的隐私信息。实验结果表明,该算法能在实际环境中稳定、有效地运行,在满足医疗数据实时一致性的同时,具有运算时间短、信息损失度小的优点。With the development of information technology,the privacy protection technology in medical data publishing has always been a hotspot in data privacy research.One of the important issues is the synchronous update of medical data publishing.To solve the synchronization problem of medical data’s anonymous publication,an algorithm based on(α,k)anonymous dataset to support dynamic update of data was proposed,i.e.,(α,k)-UPDATE.By calculating the semantic closeness,the algorithm is able to select the most similar equivalent class in(α,k)-anonymous dataset.Then the corresponding update operation is processed.The final dynamically updated dataset can satisfy(α,k)-anonymous and protect the patient’s privacy information effectively.The experimental results show that the algorithm can run stably and effectively in real environment,satisfies the real-time consistency of medical dataset and has the advantage of shorter operating time and less information loss.

关 键 词：隐私保护 数据发布 语义贴近度 (α k)-匿名 动态更新 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]