多关系关联规则挖掘中的隐私保护

Privacy preserving multi-relational association rule mining

分析了经典关联规则挖掘及相关的隐私保护等问题,同时研究了多关系关联规则的刻画和挖掘问题.通过重新定义查询模式,改进了Warmr方法,使查询模式支持"频繁查询模式的子模式也必然是频繁的"这种Apriori特性,进而将其移植到多关系规则的挖掘过程,从而加快规则的挖掘.研究了有针对性的敏感规则的挖掘方法,通过挖掘包含敏感信息的所有频繁查询模式,从中导出所有能够导致信息泄露的敏感规则;为了平衡数据可用性和安全性之间的矛盾,通过隐藏所有敏感规则中公共关系的元组,在保证规则隐藏和数据安全的同时,降低了对数据可用性的影响.

In order to overcome the drawbacks of the existing method in privacy preserving association rule mining,a new concept of multi-relational association rule is defined to describe the correlations among data in multi-relations.By using a similar Apriori property,such as sub query model of a frequent query model must be also frequent,an improved algorithm of multi-relational association rule mining is presented based on the modification on Warmr. The hiding method of sensitive multi-relational association rule...