Privacy Preserving of Classification Rules for Multiparty Computation Systems
This paper discusses the PPDM model, in which, the privacy of data transacted amongst the various parties involved is highlighted. Data mining over multiple data sources has become an important practical problem with applications in different areas. The aim is to mine the dataset available with each data custodian in a semi-honest model, securely without disclosure of any data amongst the varied custodian involved. In the proposed scheme, the data partitioning has been done in the Horizontal way, this reduces the computational complexity. The authors focus on the classification problem and the proposed model considers the C5.0 algorithm and compared with the existing techniques like ID3 and C4.5.