Abstrato

Survey of Various Techniques to Provide Multilevel Trust in Privacy Preserving Data Mining

R.Mynavathi, N.Sowmiya, D.Vanitha

The new dimension of Multilevel Trust (MLT) poses new challenges for perturbation-based PPDM. In contrast to the single-level trust scenario where only one perturbed copy is released, now multiple differently perturbed copies of the same data are available to data miners at different trusted levels.The problem of developing accurate models about aggregated data without access to precise information in individual data record is addressed. Previous solutions of this approach are limited in their assumption of single-level trust on data miners.In Single-level trust, only one perturbed copy of data is released.In the proposed system, we expand the scope of perturbation based PPDM to Multilevel Trust (MLT-PPDM). In our setting, the more trusted a data miner is, the less perturbed copy of the data it can access.A malicious data miner may have access to differently perturbed copies of the same data through various means. Prevents from jointly reconstructing the original data. Allows a data owner to generate perturbed copies of its data for arbitrary trust levels on demand. As with most existing work on perturbation-based PPDM, the existing work is limited in the sense that it considers only linear attacks (attack by single party).When two or more different parties involved in combining the perturbed copies and tries to recover the privacy, then the techniques are less suitable. More powerful adversaries may apply nonlinear techniques to derive original data and recover more information.This feature provides data owners’ more flexibility.