Decentralized Collaborative Learning Framework with External Privacy Leakage Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Idé, Tsuyoshi, Phan, Dzung T., Raymond, Rudy
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910394012925952
author Idé, Tsuyoshi
Phan, Dzung T.
Raymond, Rudy
author_facet Idé, Tsuyoshi
Phan, Dzung T.
Raymond, Rudy
contents This paper presents two methodological advancements in decentralized multi-task learning under privacy constraints, aiming to pave the way for future developments in next-generation Blockchain platforms. First, we expand the existing framework for collaborative dictionary learning (CollabDict), which has previously been limited to Gaussian mixture models, by incorporating deep variational autoencoders (VAEs) into the framework, with a particular focus on anomaly detection. We demonstrate that the VAE-based anomaly score function shares the same mathematical structure as the non-deep model, and provide comprehensive qualitative comparison. Second, considering the widespread use of "pre-trained models," we provide a mathematical analysis on data privacy leakage when models trained with CollabDict are shared externally. We show that the CollabDict approach, when applied to Gaussian mixtures, adheres to a Renyi differential privacy criterion. Additionally, we propose a practical metric for monitoring internal privacy breaches during the learning process.
format Preprint
id arxiv_https___arxiv_org_abs_2404_01270
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Decentralized Collaborative Learning Framework with External Privacy Leakage Analysis
Idé, Tsuyoshi
Phan, Dzung T.
Raymond, Rudy
Machine Learning
Cryptography and Security
Distributed, Parallel, and Cluster Computing
This paper presents two methodological advancements in decentralized multi-task learning under privacy constraints, aiming to pave the way for future developments in next-generation Blockchain platforms. First, we expand the existing framework for collaborative dictionary learning (CollabDict), which has previously been limited to Gaussian mixture models, by incorporating deep variational autoencoders (VAEs) into the framework, with a particular focus on anomaly detection. We demonstrate that the VAE-based anomaly score function shares the same mathematical structure as the non-deep model, and provide comprehensive qualitative comparison. Second, considering the widespread use of "pre-trained models," we provide a mathematical analysis on data privacy leakage when models trained with CollabDict are shared externally. We show that the CollabDict approach, when applied to Gaussian mixtures, adheres to a Renyi differential privacy criterion. Additionally, we propose a practical metric for monitoring internal privacy breaches during the learning process.
title Decentralized Collaborative Learning Framework with External Privacy Leakage Analysis
topic Machine Learning
Cryptography and Security
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2404.01270