Litcius/Paper detail

CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning

Jinhyun So, Başak Güler, A. Salman Avestimehr

2021IEEE Journal on Selected Areas in Information Theory24 citationsDOIOpen Access PDF

Abstract

How to train a machine learning model while keeping the data private and secure? We present CodedPrivateML, a fast and scalable approach to this critical problem. CodedPrivateML keeps both the data and the model information-theoretically private, while allowing efficient parallelization of training across distributed workers. We characterize CodedPrivateML's privacy threshold and prove its convergence for logistic (and linear) regression. Furthermore, via extensive experiments on Amazon EC2, we demonstrate that CodedPrivateML provides significant speedup over cryptographic approaches based on multi-party computing (MPC).

Topics & Concepts

SpeedupComputer scienceScalabilityConvergence (economics)CryptographyPrivate information retrievalInformation privacyDistributed computingLogistic regressionTheoretical computer scienceMachine learningArtificial intelligenceParallel computingData miningComputer securityDatabaseEconomicsEconomic growthPrivacy-Preserving Technologies in DataCryptography and Data SecurityStochastic Gradient Optimization Techniques