Counter Deanonymization Query: H-index Based k-Anonymization Privacy Protection for Social Networks

摘要

In this paper, we propose a novel k-anonymization scheme torncounter deanonymization queries on social networks. Withrnthis scheme, all entities are protected by k-anonymization,rnwhich means the attackers cannot re-identify a target withrnconfidence higher than 1=k. The proposed scheme minimizesrnthe modification on original networks, and accordingly maximizesrnthe utility preservation of published data while achievingrnk-anonymization privacy protection. Extensive experimentsrnon real data sets demonstrate the effectiveness of thernproposed scheme, where the efficacy of the k-anonymizedrnnetworks is verified with the distributions of pagerank, betweenness,rnand their Kolmogorov-Smirnov (K-S) test.