SecureBiNN: 3-party secure computation for binarized neural network inference

DOI10.1007/978-3-031-17143-7_14MaRDI QIDQ6109458zbMATH OpenOpenAlexFDO

Authors Wenxing Zhu, Mengqi Wei, Xiangxue Li, Qiang Li

Publication date 28 July 2023

Published in Computer Security – ESORICS 2022 (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-031-17143-7_14

zbMATH Keywords

binarized neural networkprivacy-preserving machine learningsecure multi-party computation

Mathematics Subject Classification ID

Computer security (68M25) Privacy of data (68P27) Modes of computation (nondeterministic, parallel, interactive, probabilistic, etc.) (68Q10) Learning and adaptive systems in artificial intelligence (68T05) Cryptography (94A60) Authentication, digital signatures and secret sharing (94A62)

Recommendations

• Maliciously secure matrix multiplication with applications to private deep learning
• Fast homomorphic evaluation of deep discretized neural networks
• Privacy preserving multi-party computation delegation for deep learning in cloud computing
• \textsf{Through the looking-glass}: benchmarking secure multi-party computation comparisons for \textsf{ReLU}'s
• Fast secure comparison for medium-sized integers and its application in binarized neural networks

Cites work

• Communication-efficient (client-aided) secure two-party protocols and its application
• Fast homomorphic evaluation of deep discretized neural networks
• High-throughput secure three-party computation for malicious adversaries and an honest majority
• Homomorphic encryption for arithmetic of approximate numbers
• scientific article; zbMATH DE number 1222850 (Why is no real title available?)
• Universally composable security

Cited in

(3)

• Fast secure comparison for medium-sized integers and its application in binarized neural networks
• \textsf{Through the looking-glass}: benchmarking secure multi-party computation comparisons for \textsf{ReLU}'s
• SecureTLM: private inference for transformer-based large model with MPC

This page was built for publication: SecureBiNN: 3-party secure computation for binarized neural network inference

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6109458)