A Quantization-based Technique for Privacy Preserving Distributed Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Colombo, Maurizio, Asal, Rasool, Damiani, Ernesto, AlQassem, Lamees Mahmoud, Almemari, Al Anoud, Alhammadi, Yousof
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913407011127296
author Colombo, Maurizio
Asal, Rasool
Damiani, Ernesto
AlQassem, Lamees Mahmoud
Almemari, Al Anoud
Alhammadi, Yousof
author_facet Colombo, Maurizio
Asal, Rasool
Damiani, Ernesto
AlQassem, Lamees Mahmoud
Almemari, Al Anoud
Alhammadi, Yousof
contents The massive deployment of Machine Learning (ML) models raises serious concerns about data protection. Privacy-enhancing technologies (PETs) offer a promising first step, but hard challenges persist in achieving confidentiality and differential privacy in distributed learning. In this paper, we describe a novel, regulation-compliant data protection technique for the distributed training of ML models, applicable throughout the ML life cycle regardless of the underlying ML architecture. Designed from the data owner's perspective, our method protects both training data and ML model parameters by employing a protocol based on a quantized multi-hash data representation Hash-Comb combined with randomization. The hyper-parameters of our scheme can be shared using standard Secure Multi-Party computation protocols. Our experimental results demonstrate the robustness and accuracy-preserving properties of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2406_19418
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Quantization-based Technique for Privacy Preserving Distributed Learning
Colombo, Maurizio
Asal, Rasool
Damiani, Ernesto
AlQassem, Lamees Mahmoud
Almemari, Al Anoud
Alhammadi, Yousof
Cryptography and Security
Artificial Intelligence
The massive deployment of Machine Learning (ML) models raises serious concerns about data protection. Privacy-enhancing technologies (PETs) offer a promising first step, but hard challenges persist in achieving confidentiality and differential privacy in distributed learning. In this paper, we describe a novel, regulation-compliant data protection technique for the distributed training of ML models, applicable throughout the ML life cycle regardless of the underlying ML architecture. Designed from the data owner's perspective, our method protects both training data and ML model parameters by employing a protocol based on a quantized multi-hash data representation Hash-Comb combined with randomization. The hyper-parameters of our scheme can be shared using standard Secure Multi-Party computation protocols. Our experimental results demonstrate the robustness and accuracy-preserving properties of our approach.
title A Quantization-based Technique for Privacy Preserving Distributed Learning
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2406.19418