Privacy-Preserving Hierarchical Model-Distributed Inference

Zapisane w:
Opis bibliograficzny
Wydane w:arXiv.org (Sep 15, 2024), p. n/a
1. autor: Fatemeh Jafarian Dehkordi
Kolejni autorzy: Keshtkarjahromi, Yasaman, Seferoglu, Hulya
Wydane:
Cornell University Library, arXiv.org
Hasła przedmiotowe:
Dostęp online:Citation/Abstract
Full text outside of ProQuest
Etykiety: Dodaj etykietę
Nie ma etykietki, Dołącz pierwszą etykiete!

MARC

LEADER 00000nab a2200000uu 4500
001 3085747704
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3085747704 
045 0 |b d20240915 
100 1 |a Fatemeh Jafarian Dehkordi 
245 1 |a Privacy-Preserving Hierarchical Model-Distributed Inference 
260 |b Cornell University Library, arXiv.org  |c Sep 15, 2024 
513 |a Working Paper 
520 3 |a This paper focuses on designing a privacy-preserving Machine Learning (ML) inference protocol for a hierarchical setup, where clients own/generate data, model owners (cloud servers) have a pre-trained ML model, and edge servers perform ML inference on clients' data using the cloud server's ML model. Our goal is to speed up ML inference while providing privacy to both data and the ML model. Our approach (i) uses model-distributed inference (model parallelization) at the edge servers and (ii) reduces the amount of communication to/from the cloud server. Our privacy-preserving hierarchical model-distributed inference, privateMDI design uses additive secret sharing and linearly homomorphic encryption to handle linear calculations in the ML inference, and garbled circuit and a novel three-party oblivious transfer are used to handle non-linear functions. privateMDI consists of offline and online phases. We designed these phases in a way that most of the data exchange is done in the offline phase while the communication overhead of the online phase is reduced. In particular, there is no communication to/from the cloud server in the online phase, and the amount of communication between the client and edge servers is minimized. The experimental results demonstrate that privateMDI significantly reduces the ML inference time as compared to the baselines. 
653 |a Parallel processing 
653 |a Servers 
653 |a Clients 
653 |a Data exchange 
653 |a Privacy 
653 |a Machine learning 
653 |a Communication 
653 |a Cloud computing 
653 |a Edge computing 
653 |a Inference 
653 |a Linear functions 
700 1 |a Keshtkarjahromi, Yasaman 
700 1 |a Seferoglu, Hulya 
773 0 |t arXiv.org  |g (Sep 15, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3085747704/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2407.18353