Practical Fully Homomorphic Encryption for Fully Masked Neural Networks

DOI10.1007/978-3-030-31578-8_2zbMath1444.94073OpenAlexW2979524102MaRDI QIDQ3297611

Malika Izabachène, Martin Zuber, Renaud Sirdey

Publication date: 20 July 2020

Published in: Cryptology and Network Security (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-030-31578-8_2

zbMATH Keywords

face recognitionHopfield neural networksLWEfully homomorphic encryptionGSWFHE performances

Mathematics Subject Classification ID

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

Related Items (1)

\textsf{ComBo}: a novel functional bootstrapping method for efficient evaluation of nonlinear functions in the encrypted domain

Uses Software

• TFHE

Cites Work

• Unnamed Item
• On the concrete hardness of learning with errors
• Fast homomorphic evaluation of deep discretized neural networks
• Faster packed homomorphic operations and efficient circuit bootstrapping for TFHE
• Homomorphic Encryption from Learning with Errors: Conceptually-Simpler, Asymptotically-Faster, Attribute-Based
• Faster Fully Homomorphic Encryption: Bootstrapping in Less Than 0.1 Seconds
• On Ideal Lattices and Learning with Errors over Rings
• Neural networks and physical systems with emergent collective computational abilities.
• Perceptual Color Image Coding With JPEG2000

This page was built for publication: Practical Fully Homomorphic Encryption for Fully Masked Neural Networks