基于K-匿名的隐私保护关键技术研究

Research on key technology of privacy preservation based on K-anonymity

通过对数据的挖掘,企业能提供更加精准、贴心的服务,获得更大的收益。但是数据挖掘同时也带来巨大的挑战,个人隐私保护问题就是其中之一。如何在挖掘数据时既能保护用户的个人隐私又能确保数据的可用性,隐私保护数据发布技术应运而生。文中简要介绍了该技术的基本K-匿名模型,更深入对敏感属性的研究,提出了敏感度联合矩阵。最终结合聚类算法,提出了文中的方法。结果表明,确实加强了对敏感属性隐私的保护。

By mining data, enterprise can provide more accurate, attentive service, obtaining greater benefits. But data mining also brings huge challenges,personal privacy is one ol them. H o w to protect users’ privacy information and to preserve data usability when mining data, privacy-preserving data publishing technology emerges. This article briefly describes its K-anonymity model,discusses sensitive attribute deeply,proposes joint sensitivity matrix. Finally combined with the clustering algorithm,it proposes the method. The result shows that it can really strengthen the protection of sensitive attribute privacy.