الفهرس يوجد فقط 14 صفحة متاحة للعرض العام
 |  | from | 63 |  |  |
| | | from | 63 | | |
المستخلص
’The growth ol’ computer networks with the ability to perform data collection on a large scale open up opportunities for cooperative compulation. I iowever, privacy concerns should be carefully considered. Recently, many protocols have been proposed for solving different cooperative computation problems privately.
This work addresses secure mining of association rules over horizontally partitioned data. 1 his problem is considered a special case of a general problem: Secure Multiparty Computation (SMC). The SMC problem aims at computing some function of inputs that are scattered among different parties, without having these parlies reveal their individual inputs. We present a new protocol for preserving privacy while mining association rules over horizontally partitioned data. The proposed protocol is based on the distributed implementation of /(priori algorithm and incorporates cryptographic techniques to minimize the information shared. The protocol solves the problem of mining association rules when data is partitioned between different parties. The parties want to discover association rules in the union of their data sets without leaking any information about their inputs to one another. The method presented assumes three or more parties. In the two-party case, knowing a rule is supported globally and not supported at one’s own site reveals that the other site supports the rule. Thus, much of the knowledge we try to protect is revealed even with a completely secure method for computing the global results. By the same argument, we assume no collusion, as colluding parties can reduce this to the two-party case. The protocol makes use of the homomorphic encryption feature provided by some cryptosystems for privately discovering the association rules.