Private aggregation of teacher ensembles (PATE) leads to word error rate reductions of more than 26% relative to standard differential-privacy techniques.| Amazon Science
Prize honors Amazon senior principal scientist and Penn professor for a protocol that achieves a theoretical limit on information-theoretic secure multiparty computation.| Amazon Science
Both secure multiparty computation and differential privacy protect the privacy of data used in computation, but each has advantages in different contexts.| Amazon Science