Privacy Preservation of Sensitive Data used in Datamining Task

In this paper we address the issue of privacy preservation of sensitive data used in data mining. Specifically, we consider a scenario in which party owning confidential database wish to run a data mining algorithm on their database, without revealing any unnecessary information. Our work is motivated by the need to both protect privileged information and enable its use for research or other purposes. The above problem is a specific example of secure party computation and as such, can be solved using known generic protocols. However, data mining algorithms are typically complex and, furthermore, the input usually consists of massive data sets. The generic protocols in such a case are of no practical use and therefore more efficient protocols are required. When data are to be shared between parties, some sensitive data which should be closed to the other parties since now days data sharing between two organizations is common in many application areas like marketing or business planning. Patients privacy protection is necessary and the medical data security also required. One more thing is medical records are also more sensitive, it requires to take privacy protection more seriously. As per requirement by the Health Insurance Portability and Accountability Act (HIPAA), it is necessary to protect patients privacy and the medical data security must be ensured. First we have to apply generalization on modified or randomized data, Before this we randomize the original data. This method is called privacy preserving using Hybrid approach. This technique can reconstruct original data, makes usability of data since provides data with no information loss. This technique also protects private data with better accuracy. Mainly Hill-cipher technique was applied to numerical attribute data. With this, we can maintain privacy and also partial recovery of numerical attribute is possible.