K- Dataset De-identification Method and Apparatus Using K-anonymity Model

摘要

The present invention relates to a method and apparatus for de-identifying a data set using a K-anonymity model, and the method according to the present invention comprises: checking a distribution of attribute values for each column corresponding to a quasi-identifier attribute for a non-identifying target data set , The first processing step of de-identification processing for each column of the de-identification target data set considering the distribution of the attribute values for each column, and the record with the same attribute value of one or more columns in the first-processed de-identification target data set If there are K or more, grouping records with the same attribute value into a group of records, and taking into account the distribution of attribute values in a column that does not have the same attribute value in the record group, the attribute values are not equal to satisfy the K-anonymity requirement. And subjecting the column to de-identification. According to the present invention, the K-anonymity requirement is satisfied, but data crushing can be minimized, and there is an advantage of improving the speed of de-identification processing.