Fast homomorphic evaluation of deep discretized neural networks

DOI10.1007/978-3-319-96878-0_17MaRDI QIDQ775993zbMATH OpenOpenAlexFDO

Authors Florian Bourse, Michele Minelli, Matthias Minihold, Pascal Paillier

Publication date 30 June 2020

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

zbMATH Keywords

bootstrappingfully homomorphic encryptionMNISTneural networks

Mathematics Subject Classification ID

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

Recommendations

• Practical Fully Homomorphic Encryption for Fully Masked Neural Networks
• TFHE: fast fully homomorphic encryption over the torus
• New techniques for multi-value input homomorphic evaluation and applications
• FHEW: bootstrapping homomorphic encryption in less than a second
• Large FHE gates from tensored homomorphic accumulator

Cited in

(19)

• SPEED: secure, private, and efficient deep learning
• High-precision bootstrapping of RNS-CKKS homomorphic encryption using optimal minimax polynomial approximation and inverse sine function
• Fast secure comparison for medium-sized integers and its application in binarized neural networks
• Secure transfer learning for machine fault diagnosis under different operating conditions
• Practical Fully Homomorphic Encryption for Fully Masked Neural Networks
• ML confidential: machine learning on encrypted data
• PRIORIS: Enabling Secure Detection of Suicidal Ideation from Speech Using Homomorphic Encryption
• Faster homomorphic evaluation of discrete Fourier transforms
• 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
• Encrypted classification using secure K-nearest neighbour computation
• Rotation key reduction for client-server systems of deep neural network on fully homomorphic encryption
• Full domain functional bootstrapping using the prime cyclotomic ring
• Homomorphic sign evaluation with a RNS representation of integers
• HELIOPOLIS: verifiable computation over homomorphically encrypted data from interactive oracle proofs is practical
• Accelerating TFHE with sorted bootstrapping techniques
• Parallel and memory-efficient homomorphically encrypted CNNs using vector and tensor representations

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q775993)