Data publishing Anonymity Algorithm Research Based on Clustering
Yang Yu, Longjun Zhang · 2016
Data publishing provides convenience for data exchange and data sharing.But at the same time, the issue of personal privacy information leakage has become increasingly prominent.Anonymous algorithm is one of the main technologies in data publishing environment to realize privacy protection, but most anonymity algorithm of all sensitive attributes values are treated equally, without considering their sensitivity and specific distribution.It is vulnerable to similar attacks and deviation of attack.The equivalence classes are established by clustering technique, and the different levels of privacy protection are defined for each sensitive attribute value.Using local heavy coding scheme on the identifier to anonymous, anonymity algorithm ( l , c) based on clustering is put forward.Experimental results show that the proposed algorithm improves the availability of published data while protecting privacy.