Privacy Gain Based Multi-Iterative k-Anonymization to Protect Respondents Privacy
This work addresses privacy concerns for data owners in domains like medical and financial records, but it is incremental as it builds on existing k-anonymization methods.
The paper tackles the problem of sharing data for data mining while preserving privacy by extending k-anonymization with a Privacy Gain metric for selective anonymization, resulting in preserved sensitive attributes with minimal information loss as evaluated on standard datasets.
Huge volume of data from domain specific applications such as medical, financial, telephone, shopping records and individuals are regularly generated. Sharing of these data is proved to be beneficial for data mining application. Since data mining often involves data that contains personally identifiable information and therefore releasing such data may result in privacy breaches. On one hand such data is an important asset to business decision making by analyzing it. On the other hand data privacy concerns may prevent data owners from sharing information for data analysis. In order to share data while preserving privacy, data owner must come up with a solution which achieves the dual goal of privacy preservation as well as accuracy of data mining task mainly clustering and classification. Privacy Preserving Data Publishing (PPDP) is a study of eliminating privacy threats like linkage attack while preserving data utility by anonymizing data set before publishing. Proposed work is an extension to k-anonymization where Privacy Gain (PrGain) has been computed for selective anonymization for set of tuples. Classification and clustering characteristics of original data and anonymized data using proposed algorithm have been evaluated in terms of information loss, execution time, and privacy achieved. Algorithm has been processed against standard data sets and analysis shows that values for sensitive attributes are being preserved with minimal information loss.