Fast secure comparison for medium-sized integers and its application in binarized neural networks

DOI10.1007/978-3-030-12612-4_23MaRDI QIDQ2290467zbMATH OpenOpenAlexFDO

Authors M. Abspoel, Niek Bouman, Berry Schoenmakers, Niels de Vreede

Publication date 28 January 2020

Full work available at URL https://ir.cwi.nl/pub/28602

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Authentication, digital signatures and secret sharing (94A62)

Recommendations

• SecureBiNN: 3-party secure computation for binarized neural network inference
• Improved secure integer comparison via homomorphic encryption
• Fast homomorphic evaluation of deep discretized neural networks
• Positional characteristics for efficient number comparison over the homomorphic encryption
• Practical and Secure Solutions for Integer Comparison
• SPEED: secure, private, and efficient deep learning
• Practical Fully Homomorphic Encryption for Fully Masked Neural Networks
• Numerical method for comparison on homomorphically encrypted numbers
• Enabling Secure NVM-Based in-Memory Neural Network Computing by Sparse Fast Gradient Encryption
• Efficient homomorphic comparison methods with optimal complexity

Cited in

(5)

• A note on secure multiparty computation via higher residue symbols
• SecureBiNN: 3-party secure computation for binarized neural network inference
• Secure function extensions to additively homomorphic cryptosystems
• Circuit privacy for FHEW/TFHE-style fully homomorphic encryption in practice
• On circuit private, multikey and threshold approximate homomorphic encryption

This page was built for publication: Fast secure comparison for medium-sized integers and its application in binarized neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2290467)