Authors:
Laurent Gomez
1
;
Alberto Ibarrondo
1
;
José Márquez
1
and
Patrick Duverger
2
Affiliations:
1
SAP Security Research, 805, Avenue Dr. Maurice Donat, 06250 Sophia-Antipolis and France
;
2
City of Antibes Juan-les-Pins and France
Keyword(s):
Intellectual Property Protection, Fully Homomorphic Encryption, Neural Networks, Distributed Landscapes, Smart Cities.
Related
Ontology
Subjects/Areas/Topics:
Data and Application Security and Privacy
;
Data Protection
;
Information and Systems Security
;
Information Assurance
;
Intellectual Property Protection
;
Security in Distributed Systems
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.
(More)