Privacy‐enhancing machine learning framework with private aggregation of teacher ensembles
Sign Up to like & getrecommendations! Published in 2022 at "International Journal of Intelligent Systems"
DOI: 10.1002/int.23020
Abstract: Private aggregation of teacher ensembles (PATE), a general machine learning framework based on knowledge distillation, can provide a privacy guarantee for training data sets. However, this framework poses a number of security risks. First, PATE… read more here.
Keywords: aggregation; aggregation teacher; framework; privacy ... See more keywords
Private Aggregation With Application to Distributed Optimization
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Control Systems Letters"
DOI: 10.1109/lcsys.2020.3041611
Abstract: This letter presents a fully distributed private aggregation protocol that can be employed in dynamical networks where communication is only assumed on a neighbor-to-neighbor basis. The novelty of the scheme is its low overhead in… read more here.
Keywords: aggregation application; application distributed; aggregation; private aggregation ... See more keywords