A novel approach for privacy mining of generic basic association rules
Moez Waddey, Pascal Poncelet, Sadok Ben Yahia · 2009
Data mining can extract important knowledge from large data collections - but sometimes these collections are split among various parties. Privacy concerns may prevent the parties from directly sharing the data. The irony is that data mining results rarely violate privacy. The objective of data mining is to generalize across populations rather than reveal information about individuals [10]. Thus, the true problem is not data mining, but how data mining is done. This paper presents a new scalable algorithm for discovering closed frequent itemsets in distributed environment, using commutative encryption to ensure privacy concerns. We address secure mining of association rules over horizontally partitioned data.