A Review on Various Privacy Preserving Techniuqes & Classifications Algorithms
Ankita Jain, Shubha Dubey, Anurag Jain · 2014
Privacy preserving data mining is one of the most demanding research areas within the data mining community. In many cases, multiple parties may wish to share aggregate private data without disclosing any private information at user side. Over the last few years this has naturally lead to a growing interest in security or privacy issues in data mining. More precisely, it became clear that discovering knowledge through a combination of different databases raises important security issues. New dimension of structure Trust (MLT) poses new challenges for perturbation- based PPDM. In distinction to the single-level trust situation wherever just one rattled copy is released, currently multiple otherwise rattled copies of the same knowledge are offered to knowledge miners at completely different sure levels. The a lot of sure an information manual labourer is, the less rattled copy it will access; it's going to even have access to the rattled copies offered at lower trust levels. In this paper we are presenting some techniques to overcome problems related with privacy preservation and multi-level trust.