摘要 |
A first party has a data vector x and a second party has a classifier defined as a set of multivariate Gaussian distributions. A secure inner dot product procedure is applied to each multivariate Gaussian distribution and the data vector x to produce a vector a<SUB>i </SUB>for the first party and a vector b<SUB>i </SUB>for the second party for each application. The secure inner dot product is then applied to each vector b<SUB>i </SUB>and the data vector x to produce a scalar r<SUB>i </SUB>for the first party and a scalar q<SUB>i </SUB>for the second party for each application. A summed vector of elements [(a<SUB>1</SUB>x+q<SUB>1</SUB>+r<SUB>1</SUB>), . . . , (a<SUB>N</SUB>x+q<SUB>N</SUB>+r<SUB>N</SUB>)] is formed, and an index I of the summed vector for a particular element having a maximum value is the class of the data vector x.
|