Analysis of data security by using anonymization techniques
Preet Chandan Kaur, Tushar H. Ghorpade, Vanita Manikrao Mane · 2016
Modern technology generates such a huge amount of public and private datasets that its security becomes an inevitable task. Initially the priority was provided for data security for the data of organization's and firm's, but nowadays it is necessary to provide security for personal data as well. So to achieve the data security, it is mandatory to preserve the privacy of personal information for that we use anonymization technique such as generalization, bucketization, multi set-based generalization, one-attribute-per-column slicing, slicing and suppression with slicing are applied to avoid retrieval of data from database. Thus, privacy preservation means to protect the data value and it is used for data mining in order to get the valid and accurate results. These are discussed and successfully analyzed with different parameters such as revealed co-relation quality (linkage property), loss of information, type of data, security (privacy preserved) and membership disclosure in this paper. The analysis shows that suppression with slicing is an innovative technique that preserves the privacy of identity of an individual in a database better than previously mentioned techniques.