Applying a differential privacy operation on a cluster of data

A system for data anonymity in a computing environment, comprising:

• one or more computers with executable instructions that when executed cause the system to:
• receive a dataset by the processor, the dataset comprising records stored in a database;
• wherein the records include a plurality of defined fields, some of the plurality of defined fields including at least categorical and numerical attributes;
• define, through a user interface, a first algorithm for a differential privacy operation and a second algorithm for a clustering operation to be performed on the dataset;
• transform the dataset by the processor into an anonymous dataset by applying the differential privacy operation and the clustering operation to the dataset;
• wherein the differential privacy operation is applied to each cluster of data obtained from the clustering operation such that the clustering operation is applied to a first subset of the plurality of defined fields of the records and the differential privacy operation is applied to a second, remaining subset of the plurality of defined fields of the records;
• and wherein, responsive to a completion of both the clustering operation and the differential privacy operation, the records of the dataset are shuffled as reorganized in the database;
• and
• output and store, by the processor, the transformed dataset as the anonymous dataset having a specified level of privacy according to the differential privacy operation such that k-anonymity is achieved on the plurality of defined fields including both the categorical and numerical attributes of the dataset transformed by the differential privacy operation into the anonymous dataset.

A computer program product for, by a processor, data anonymity within a computing environment, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:

• an executable portion that receives a dataset by the processor, the dataset comprising records stored in a database;
• wherein the records include a plurality of defined fields, some of the plurality of defined fields including at least categorical and numerical attributes;
• an executable portion that defines, through a user interface, a first algorithm for a differential privacy operation and a second algorithm for a clustering operation to be performed on the dataset;
• an executable portion that transforms the dataset by the processor into an anonymous dataset by applying the differential privacy operation and the clustering operation to the dataset;
• wherein the differential privacy operation is applied to each cluster of data obtained from the clustering operation such that the clustering operation is applied to a first subset of the plurality of defined fields of the records and the differential privacy operation is applied to a second, remaining subset of the plurality of defined fields of the records;
• and wherein, responsive to a completion of both the clustering operation and the differential privacy operation, the records of the dataset are shuffled as reorganized in the database;
• and
• an executable portion that outputs and stores, by the processor, the transformed dataset as the anonymous dataset having a specified level of privacy according to the differential privacy operation such that k-anonymity is achieved on the plurality of defined fields including both the categorical and numerical attributes of the dataset transformed by the differential privacy operation into the anonymous dataset.