Abstract: With advances of network-based services and smart phones, various
types of information tightly associated with individual and
organizational activities are being collected. Privacy-preserving
data mining (PPDM) is now gaining much attention as technologies which
enable secure exploitation of such sensitive information. In the talk,
privacy preserving data mining with homomorphic encryption, which
allows a certain prescribed operation, such as addiction or
multiplication, over encrypted values, are introduced. Furthermore, we
demonstrate our development framework for PPDM with smart phones,
fairy ring. As advanced topics of PPDM, we consider multiparty
computation in which parties form a graph and the links between
parties and the information held by the parties are private, and show
that well-known network mining problems, such as PageRank and label
propagation, can be realized over the private graph of parties.
|