Implementing Privacy-Preserving Bayesian-Net Discovery for Vertically Partitioned Data

The great potential of data mining in a networked world cannot be realized without acceptable guarantees that private information will be protected. In theory, general cryptographic protocols for secure multiparty computation enable data mining with privacy preservation that is optimal with respect to the desired end results. However, the performance expense of such general protocols is prohibitive if applying the technology naively to non-trivial databases. The gap between theory and practice in cryptographic approaches is being narrowed, in part, by the introduction of problemspecific secure computation protocols. We describe our implementation of the recent YangWright secure protocol for Bayes-net discovery in vertically partitioned data. Our development occasions the proposal of a general coordination architecture for assembly of modularly described, complex protocols from independently implemented and tested subprotocol building blocks, which should facilitate future similar implementation efforts.