Cover Image

Privacy-Preserving Hierarchical Model-Distributed Inference

Saved in:
Published in:arXiv.org (Sep 15, 2024), p. n/a
Main Author: Fatemeh Jafarian Dehkordi
Other Authors: Keshtkarjahromi, Yasaman, Seferoglu, Hulya
Published:
Cornell University Library, arXiv.org
Subjects:
Parallel processing
Servers
Clients
Data exchange
Privacy
Machine learning
Communication
Cloud computing
Edge computing
Inference
Linear functions
Online Access:Citation/Abstract
Full text outside of ProQuest
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: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.
ISSN:2331-8422
Source:Engineering Database