社会网络数据中一种基于k-degree-l-diversity匿名的个性化隐私保护方法

A Personalized Privacy Preserving Method Based on k-degree-l-diversity Anonymity for Social Network Data

近年来关于社会网络数据的隐私保护方法中,大部分将社会网络中的所有个体考虑为具有相同等级的隐私保护需求,没有考虑其隐私需求是多样化和个性化的,故会对某些个体存在过度保护,造成数据不必要的失真。基于此,在k-degree-l-diversity匿名方法的基础上提出了个性化-(k,l)匿名方法。实验证明,该个性化匿名方法能减少数据的损失,提高数据的可用性。

In recent research about privacy preserving for social network, most of the methods focus on the same level privacy requirement for all individuals, and do not consider that individuals＇ privacy requirement is various and personalized. Thus can cause ＂excessive protection＂ to some individuals, and then bring unnecessary data distortion. Motivated by this, proposes the personalized-（k, l） anonymity method based on k-degree-l-diversity anonymity method. The experiment shows that the personalized anonymous method can reduce the data distortion and improve the utility of the data.