Efficient Recommendation of De-identification Policies using Map Reduce - 2017

PROJECT TITLE :

Efficient Recommendation of De-identification Policies using Map Reduce - 2017

ABSTRACT:

Abstract—Several information homeowners are required to unharness the info during a selection of real world application, since it's of very important importance to discovery valuable data stay behind the information. However, existing re-identification attacks on the AOL and ADULTS datasets have shown that publish such information directly might cause tremendous threads to the individual privacy. Thus, it's urgent to resolve all kinds of re-identification risks by recommending effective de-identification policies to guarantee each privacy and utility of the info. De-identification policies is one of the models which will be used to achieve such needs, however, the amount of de-identification policies is exponentially large thanks to the broad domain of quasi-identifier attributes. To better control the trade off between information utility and data privacy, skyline computation will be used to select such policies, but it's however challenging for efficient skyline processing over large variety of policies. During this paper, we tend to propose one parallel algorithm known as SKY-FILTER-MR, which is predicated on MapReduce to overcome this challenge by computing skylines over large scale de-identification policies that is represented by bit-strings. To any improve the performance, a unique approximate skyline computation scheme was proposed to prune unqualified policies using the approximately domination relationship. With approximate skyline, the power of filtering in the policy house generation stage was greatly strengthened to effectively decrease the cost of skyline computation over different policies. Extensive experiments over each real life and synthetic datasets demonstrate that our proposed SKY-FILTER-MR algorithm substantially outperforms the baseline approach by up to four times faster in the optimal case, that indicates smart scalability over large policy sets.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here