Intellectual Property Protection for Distributed Neural Networks - Towards Confidentiality of Data, Model, and Inference

Laurent Gomez, Alberto Ibarrondo, José Márquez, Patrick Duverger

Abstract

Capitalizing on recent advances on HPC, GPUs, GPGPUs along with the rising amounts of publicly available labeled data; (Deep) Neural Networks (NN) have and will revolutionize virtually every current application domain as well as enable novel ones such as those on recognition, autonomous, predictive, resilient, self-managed, adaptive, and evolving applications. Nevertheless, it is to point out that NN training is rather resource intensive in data, time and energy; turning the resulting trained models into valuable assets representing an Intellectual Property (IP) imperatively worth of being protected. Furthermore, in the wake of Edge computing, NNs are being progressively deployed across decentralized landscapes; as a consequence, IP owners take very seriously the protection of their NN based software products. In this paper we propose to leverage Fully Homomorphic Encryption (FHE) to protect simultaneously the IP of trained NN based software, as well as the input data and inferences. Within the context of a smart city scenario, we outline our NN model-agnostic approach, approximating and decomposing the NN operations into linearized transformations while employing a Single Instruction Multiple Data (SIMD) for vectorizing operations.

Download


Paper Citation


in Harvard Style

Gomez L., Ibarrondo A., Márquez J. and Duverger P. (2018). Intellectual Property Protection for Distributed Neural Networks - Towards Confidentiality of Data, Model, and Inference.In Proceedings of the 15th International Joint Conference on e-Business and Telecommunications - Volume 1: SECRYPT, ISBN 978-989-758-319-3, pages 147-154. DOI: 10.5220/0006854701470154


in Bibtex Style

@conference{secrypt18,
author={Laurent Gomez and Alberto Ibarrondo and José Márquez and Patrick Duverger},
title={Intellectual Property Protection for Distributed Neural Networks - Towards Confidentiality of Data, Model, and Inference},
booktitle={Proceedings of the 15th International Joint Conference on e-Business and Telecommunications - Volume 1: SECRYPT,},
year={2018},
pages={147-154},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006854701470154},
isbn={978-989-758-319-3},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on e-Business and Telecommunications - Volume 1: SECRYPT,
TI - Intellectual Property Protection for Distributed Neural Networks - Towards Confidentiality of Data, Model, and Inference
SN - 978-989-758-319-3
AU - Gomez L.
AU - Ibarrondo A.
AU - Márquez J.
AU - Duverger P.
PY - 2018
SP - 147
EP - 154
DO - 10.5220/0006854701470154