Source Anonymity for Private Random Walk Decentralized Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Egger, Maximilian, Lage, Svenja, Bitar, Rawad, Wachter-Zeh, Antonia
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915282963922944
author Egger, Maximilian
Lage, Svenja
Bitar, Rawad
Wachter-Zeh, Antonia
author_facet Egger, Maximilian
Lage, Svenja
Bitar, Rawad
Wachter-Zeh, Antonia
contents This paper considers random walk-based decentralized learning, where at each iteration of the learning process, one user updates the model and sends it to a randomly chosen neighbor until a convergence criterion is met. Preserving data privacy is a central concern and open problem in decentralized learning. We propose a privacy-preserving algorithm based on public-key cryptography and anonymization. In this algorithm, the user updates the model and encrypts the result using a distant user's public key. The encrypted result is then transmitted through the network with the goal of reaching that specific user. The key idea is to hide the source's identity so that, when the destination user decrypts the result, it does not know who the source was. The challenge is to design a network-dependent probability distribution (at the source) over the potential destinations such that, from the receiver's perspective, all users have a similar likelihood of being the source. We introduce the problem and construct a scheme that provides anonymity with theoretical guarantees. We focus on random regular graphs to establish rigorous guarantees.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07011
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Source Anonymity for Private Random Walk Decentralized Learning
Egger, Maximilian
Lage, Svenja
Bitar, Rawad
Wachter-Zeh, Antonia
Cryptography and Security
Distributed, Parallel, and Cluster Computing
Information Theory
Machine Learning
This paper considers random walk-based decentralized learning, where at each iteration of the learning process, one user updates the model and sends it to a randomly chosen neighbor until a convergence criterion is met. Preserving data privacy is a central concern and open problem in decentralized learning. We propose a privacy-preserving algorithm based on public-key cryptography and anonymization. In this algorithm, the user updates the model and encrypts the result using a distant user's public key. The encrypted result is then transmitted through the network with the goal of reaching that specific user. The key idea is to hide the source's identity so that, when the destination user decrypts the result, it does not know who the source was. The challenge is to design a network-dependent probability distribution (at the source) over the potential destinations such that, from the receiver's perspective, all users have a similar likelihood of being the source. We introduce the problem and construct a scheme that provides anonymity with theoretical guarantees. We focus on random regular graphs to establish rigorous guarantees.
title Source Anonymity for Private Random Walk Decentralized Learning
topic Cryptography and Security
Distributed, Parallel, and Cluster Computing
Information Theory
Machine Learning
url https://arxiv.org/abs/2505.07011