Byzantine-Robust Decentralized Federated Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fang, Minghong, Zhang, Zifan, Hairi, Khanduri, Prashant, Liu, Jia, Lu, Songtao, Liu, Yuchen, Gong, Neil
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917721373933568
author Fang, Minghong
Zhang, Zifan
Hairi
Khanduri, Prashant
Liu, Jia
Lu, Songtao
Liu, Yuchen
Gong, Neil
author_facet Fang, Minghong
Zhang, Zifan
Hairi
Khanduri, Prashant
Liu, Jia
Lu, Songtao
Liu, Yuchen
Gong, Neil
contents Federated learning (FL) enables multiple clients to collaboratively train machine learning models without revealing their private training data. In conventional FL, the system follows the server-assisted architecture (server-assisted FL), where the training process is coordinated by a central server. However, the server-assisted FL framework suffers from poor scalability due to a communication bottleneck at the server, and trust dependency issues. To address challenges, decentralized federated learning (DFL) architecture has been proposed to allow clients to train models collaboratively in a serverless and peer-to-peer manner. However, due to its fully decentralized nature, DFL is highly vulnerable to poisoning attacks, where malicious clients could manipulate the system by sending carefully-crafted local models to their neighboring clients. To date, only a limited number of Byzantine-robust DFL methods have been proposed, most of which are either communication-inefficient or remain vulnerable to advanced poisoning attacks. In this paper, we propose a new algorithm called BALANCE (Byzantine-robust averaging through local similarity in decentralization) to defend against poisoning attacks in DFL. In BALANCE, each client leverages its own local model as a similarity reference to determine if the received model is malicious or benign. We establish the theoretical convergence guarantee for BALANCE under poisoning attacks in both strongly convex and non-convex settings. Furthermore, the convergence rate of BALANCE under poisoning attacks matches those of the state-of-the-art counterparts in Byzantine-free settings. Extensive experiments also demonstrate that BALANCE outperforms existing DFL methods and effectively defends against poisoning attacks.
format Preprint
id arxiv_https___arxiv_org_abs_2406_10416
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Byzantine-Robust Decentralized Federated Learning
Fang, Minghong
Zhang, Zifan
Hairi
Khanduri, Prashant
Liu, Jia
Lu, Songtao
Liu, Yuchen
Gong, Neil
Cryptography and Security
Distributed, Parallel, and Cluster Computing
Machine Learning
Federated learning (FL) enables multiple clients to collaboratively train machine learning models without revealing their private training data. In conventional FL, the system follows the server-assisted architecture (server-assisted FL), where the training process is coordinated by a central server. However, the server-assisted FL framework suffers from poor scalability due to a communication bottleneck at the server, and trust dependency issues. To address challenges, decentralized federated learning (DFL) architecture has been proposed to allow clients to train models collaboratively in a serverless and peer-to-peer manner. However, due to its fully decentralized nature, DFL is highly vulnerable to poisoning attacks, where malicious clients could manipulate the system by sending carefully-crafted local models to their neighboring clients. To date, only a limited number of Byzantine-robust DFL methods have been proposed, most of which are either communication-inefficient or remain vulnerable to advanced poisoning attacks. In this paper, we propose a new algorithm called BALANCE (Byzantine-robust averaging through local similarity in decentralization) to defend against poisoning attacks in DFL. In BALANCE, each client leverages its own local model as a similarity reference to determine if the received model is malicious or benign. We establish the theoretical convergence guarantee for BALANCE under poisoning attacks in both strongly convex and non-convex settings. Furthermore, the convergence rate of BALANCE under poisoning attacks matches those of the state-of-the-art counterparts in Byzantine-free settings. Extensive experiments also demonstrate that BALANCE outperforms existing DFL methods and effectively defends against poisoning attacks.
title Byzantine-Robust Decentralized Federated Learning
topic Cryptography and Security
Distributed, Parallel, and Cluster Computing
Machine Learning
url https://arxiv.org/abs/2406.10416