FRIDA: Free-Rider Detection using Privacy Attacks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Recasens, Pol G., Horváth, Ádám, Gutierrez-Torre, Alberto, Torres, Jordi, Berral, Josep Ll., Pejó, Balázs
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914046556504064
author Recasens, Pol G.
Horváth, Ádám
Gutierrez-Torre, Alberto
Torres, Jordi
Berral, Josep Ll.
Pejó, Balázs
author_facet Recasens, Pol G.
Horváth, Ádám
Gutierrez-Torre, Alberto
Torres, Jordi
Berral, Josep Ll.
Pejó, Balázs
contents Federated learning is increasingly popular as it enables multiple parties with limited datasets and resources to train a machine learning model collaboratively. However, similar to other collaborative systems, federated learning is vulnerable to free-riders - participants who benefit from the global model without contributing. Free-riders compromise the integrity of the learning process and slow down the convergence of the global model, resulting in increased costs for honest participants. To address this challenge, we propose FRIDA: free-rider detection using privacy attacks. Instead of focusing on implicit effects of free-riding, FRIDA utilizes membership and property inference attacks to directly infer evidence of genuine client training. Our extensive evaluation demonstrates that FRIDA is effective across a wide range of scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2410_05020
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FRIDA: Free-Rider Detection using Privacy Attacks
Recasens, Pol G.
Horváth, Ádám
Gutierrez-Torre, Alberto
Torres, Jordi
Berral, Josep Ll.
Pejó, Balázs
Machine Learning
Cryptography and Security
Federated learning is increasingly popular as it enables multiple parties with limited datasets and resources to train a machine learning model collaboratively. However, similar to other collaborative systems, federated learning is vulnerable to free-riders - participants who benefit from the global model without contributing. Free-riders compromise the integrity of the learning process and slow down the convergence of the global model, resulting in increased costs for honest participants. To address this challenge, we propose FRIDA: free-rider detection using privacy attacks. Instead of focusing on implicit effects of free-riding, FRIDA utilizes membership and property inference attacks to directly infer evidence of genuine client training. Our extensive evaluation demonstrates that FRIDA is effective across a wide range of scenarios.
title FRIDA: Free-Rider Detection using Privacy Attacks
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2410.05020