Privacy Preserving Data Mining (PPDM) addresses the problem of developing accurate models about aggregated data without access to precise information in individual data record. In our setting, the more trusted a data miner is the less perturbed copy of the data (original) it can access.


 Under this setting, a malicious data miner may have access to differently perturbed copies of the fake data through various means, and may combine these diverse copies to jointly infer additional information about the fake data and the data owner does not intend to release.


To Preventing diversity attacks is the key challenge of providing multi security in Privacy Preserving Data Mining services. We address this challenge by properly correlating perturbation across copies at different trust levels. We prove that our solution is robust against diversity attacks with respect to our privacy goal. Our solution allows generating perturbed copies of fake data for arbitrary trust levels on demand.