SECURED MULTIPARTY DATA FUSION AND EXTRACTION OF PRIVATE
Keywords:
-Semi-honest adversary, vertically partitioned, Quasi-identifier (QID), privacy preserving data mining, multi party computationAbstract
Privacy-preserving data publishing addresses the problem of disclosing sensitive data when mining for useful
information. The problem of private data publishing, where different attributes for the same set of individuals are held by
two parties is addressed by a two party authentication algorithm. In particular, an algorithm for differentially private
data release for vertically partitioned data between two parties in their semi-honest adversary model is proposed. The
proposed algorithm is applied to the banking system where private data of the customers are required for banking and
for the data maintenance. In the banking system there is no differentiability in the private data each data will be
processed and retrieved from the distinct data base only. The data will be processed from two distinct and different
databases. Each data has unique link between them using that link the data will be retrieved. Exraction of New Data
from the Merged Data is performed. The implementation is all about Company Employee who has got Loan. Employee
ID plays as Primary Key and the List of Loan obtainers can be identified. Data is analyzed only by the Authorized
Persons. The security of the private data of the employee transferred between the company and the bank is enhanced and
the results are stored in the data base.
