Paper 2023/1918
FANNG-MPC: Framework for Artificial Neural Networks and Generic MPC
, Technology Innovation Institute, Technology Innovation Institute, Ruhr-University Bochum, Technology Innovation Institute, Ruhr-University Bochum, Technology Innovation Institute, Technology Innovation Institute, Technology Innovation Institute, Technology Innovation Institute, Technology Innovation Institute, Technology Innovation InstituteAbstract
In this work, we introduce FANNG-MPC, a versatile secure multi-party computation framework capable to offer active security for privacy preserving machine learning as a service (MLaaS). Derived from the now deprecated SCALE-MAMBA, FANNG is a data-oriented fork, featuring novel set of libraries and instructions for realizing private neural networks, effectively reviving the popular framework. To the best of our knowledge, FANNG is the first MPC framework to offer actively secure MLaaS in the dishonest majority setting, specifically two parties. FANNG goes beyond SCALE-MAMBA by decoupling offline and online phases and materializing the dealer model in software, enabling a separate set of entities to produce offline material. The framework incorporates database support, a new instruction set for pre-processed material, including garbled circuits and convolutional and matrix multiplication triples. FANNG also implements novel private comparison protocols and an optimized library supporting Neural Network functionality. All our theoretical claims are substantiated by an extensive evaluation using an open-sourced implementation, including the private evaluation of popular neural networks like LeNet and VGG16.
Metadata
- Available format(s)
-
PDF
- Category
- Cryptographic protocols
- Publication info
- Preprint.
- Keywords
- Multi-Party ComputationPrivacy-Preserving Machine LearningHomomorphic EncryptionNeural NetworksMPCPPML
- Contact author(s)
-
najwa aaraj @ tii ae
abdelrahaman aly @ gmail com
tim gueneysu @ rub de
chiara marcolla @ tii ae
johannes mono @ rub de
rogerio paludo @ tii ae
ivan santos @ tii ae
mireia scholz @ tii ae
eduardo soria-vazquez @ tii ae
victor sucasas @ tii ae
ajith suresh @ tii ae - History
- 2023-12-15: approved
- 2023-12-14: received
- See all versions
- Short URL
- https://ia.cr/2023/1918
- License
-
CC BY-SA
BibTeX
@misc{cryptoeprint:2023/1918,
author = {Najwa Aaraj and Abdelrahaman Aly and Tim Güneysu and Chiara Marcolla and Johannes Mono and Rogerio Paludo and Iván Santos-González and Mireia Scholz and Eduardo Soria-Vazquez and Victor Sucasas and Ajith Suresh},
title = {FANNG-MPC: Framework for Artificial Neural Networks and Generic MPC},
howpublished = {Cryptology ePrint Archive, Paper 2023/1918},
year = {2023},
note = {\url{https://eprint.iacr.org/2023/1918}},
url = {https://eprint.iacr.org/2023/1918}
}
