Fast homomorphic evaluation of deep discretized neural networks

DOI10.1007/978-3-319-96878-0_17zbMath1462.94031OpenAlexW2794888826MaRDI QIDQ775993

Matthias Minihold, Florian Bourse, Michele Minelli, Pascal Paillier

Publication date: 30 June 2020

Full work available at URL: https://zenodo.org/record/2594563

zbMATH Keywords

neural networksbootstrappingfully homomorphic encryptionMNIST

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Cryptography (94A60)

Related Items (7)

PRIORIS: Enabling Secure Detection of Suicidal Ideation from Speech Using Homomorphic Encryption ⋮ Discretization error reduction for high precision torus fully homomorphic encryption ⋮ SecureBiNN: 3-party secure computation for binarized neural network inference ⋮ \textsf{ComBo}: a novel functional bootstrapping method for efficient evaluation of nonlinear functions in the encrypted domain ⋮ Utility/privacy trade-off as regularized optimal transport ⋮ Practical Fully Homomorphic Encryption for Fully Masked Neural Networks ⋮ High-precision bootstrapping of RNS-CKKS homomorphic encryption using optimal minimax polynomial approximation and inverse sine function

This page was built for publication: Fast homomorphic evaluation of deep discretized neural networks