Efficient sanitization of unsafe data correlations
Abstract
In this paper, we present a study to counter privacy violation due to unsafe data correlation. We propose a safe correlation requirement to keep correlated values bounded by l-diversity and evaluate the trade-off to be made for the sake of a strong privacy guarantee. Finally, we present a correlation sanitization algorithm that enforces our safety constraint and demonstrates its eficiency.
DOI/handle
http://hdl.handle.net/10576/56735Collections
- Computer Science & Engineering [2284 items ]