Data mining services require accurate input data for their results to be meaningful, but privacy concerns may impel users to provide spurious information. In this chapter, we study the different aspects of privacy that arise in association rule mining, with special emphasis on input data privacy, output rule privacy and owner privacy. For input privacy, we examine whether users could be encouraged to provide accurate data by ensuring that the mining process cannot, with any reasonable degree of certainty, discover specific information that violates their privacy. Then, in the context of output privacy, we present a taxonomy and a survey of recent approaches that have been applied to the association rule hiding problem. Here, the objective is to minimally modify the original database in a manner that makes the sensitive association rules to disappear while retaining the non-sensitive rules. Finally, we study popular cryptographic methods for preserving the privacy of the individual sources participating in distributed association rule mining.
CITATION STYLE
Gkoulalas-Divanis, A., Haritsa, J., & Kantarcioglu, M. (2014). Privacy issues in association rule mining. In Frequent Pattern Mining (Vol. 9783319078212, pp. 369–401). Springer International Publishing. https://doi.org/10.1007/978-3-319-07821-2_15
Mendeley helps you to discover research relevant for your work.