• 主题
高级搜索  >
历史搜索 清空历史
首页> 美国卫生研究院文献>SpringerPlus >Anatomisation with slicing: a new privacy preservation approach for multiple sensitive attributes
【2h】

Anatomisation with slicing: a new privacy preservation approach for multiple sensitive attributes

机译：切片解剖：一种针对多种敏感属性的新隐私保护方法

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务，本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文，但由于OA文献来源多样且变更频繁，仍可能出现获取不到、文献不完整或与标题不符等情况，如果获取不到我们将提供退款服务。请知悉。
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

An enormous quantity of personal health information is available in recent decades and tampering of any part of this information imposes a great risk to the health care field. Existing anonymization methods are only apt for single sensitive and low dimensional data to keep up with privacy specifically like generalization and bucketization. In this paper, an anonymization technique is proposed that is a combination of the benefits of anatomization, and enhanced slicing approach adhering to the principle of k-anonymity and l-diversity for the purpose of dealing with high dimensional data along with multiple sensitive data. The anatomization approach dissociates the correlation observed between the quasi identifier attributes and sensitive attributes (SA) and yields two separate tables with non-overlapping attributes. In the enhanced slicing algorithm, vertical partitioning does the grouping of the correlated SA in ST together and thereby minimizes the dimensionality by employing the advanced clustering algorithm. In order to get the optimal size of buckets, tuple partitioning is conducted by MFA. The experimental outcomes indicate that the proposed method can preserve privacy of data with numerous SA. The anatomization approach minimizes the loss of information and slicing algorithm helps in the preservation of correlation and utility which in turn results in reducing the data dimensionality and information loss. The advanced clustering algorithms prove its efficiency by minimizing the time and complexity. Furthermore, this work sticks to the principle of k-anonymity, l-diversity and thus avoids privacy threats like membership, identity and attributes disclosure.
机译：在最近的几十年中，可获得大量的个人健康信息，并且对该信息的任何部分进行篡改都会给医疗保健领域带来巨大风险。现有的匿名化方法仅适用于单个敏感的低维数据，以跟上隐私保护，特别是泛化和存储桶化。在本文中，提出了一种匿名化技术，该技术结合了解剖学的好处和增强的切片方法，该方法遵循k-匿名性和l-多样性的原则，用于处理高维数据以及多个敏感数据。解剖方法分离了在准标识符属性和敏感属性（SA）之间观察到的相关性，并生成了两个具有不重叠属性的单独表。在增强的切片算法中，垂直分割将ST中的相关SA分组在一起，从而通过使用高级聚类算法将维数最小化。为了获得最佳的存储桶大小，MFA进行了元组划分。实验结果表明，该方法可以通过大量SA来保护数据的隐私。解剖方法最大程度地减少了信息丢失，并且切片算法有助于保持相关性和实用性，进而减少了数据维数和信息丢失。先进的聚类算法通过最小化时间和复杂性来证明其效率。此外，这项工作坚持了k-匿名性，l-多样性的原则，因此避免了诸如成员资格，身份和属性披露之类的隐私威胁。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号