Differential Privacy Preserving in Big Data Analytics for Connected Health
Differential Privacy Preserving in Big Data Analytics for Connected Health
复制标题
互联健康大数据分析中的差异化隐私保护
DOI：
10.1007/s10916-016-0446-0
复制
发表时间：
2016-04-01
影响因子：
5.3
通讯作者：
Wu, Guowei
中科院分区：
文献类型：
--
作者：
Lin, Chi;Song, Zihao;Wu, Guowei
在身体区域网络(BANS)中，可穿戴传感器收集的大数据通常包含敏感信息，这些信息必须得到适当的保护。以往的方法忽视了隐私保护问题，导致隐私暴露。针对车身传感器网络中的大数据，提出了一种差异化隐私保护方案。与以往的方法相比，该方案将以更高的可用性和可靠性提供隐私保护。我们引入了动态噪声阈值的概念，使我们的方案更适合处理大数据。实验结果表明，即使攻击者具有充分的背景知识，该方案仍然能够对大量敏感数据提供足够的干扰，从而保护隐私。
In Body Area Networks (BANs), big data collected by wearable sensors usually contain sensitive information, which is compulsory to be appropriately protected. Previous methods neglected privacy protection issue, leading to privacy exposure. In this paper, a differential privacy protection scheme for big data in body sensor network is developed. Compared with previous methods, this scheme will provide privacy protection with higher availability and reliability. We introduce the concept of dynamic noise thresholds, which makes our scheme more suitable to process big data. Experimental results demonstrate that, even when the attacker has full background knowledge, the proposed scheme can still provide enough interference to big sensitive data so as to preserve the privacy.