CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning
Jinhyun So, Başak Güler, A. Salman Avestimehr
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