On the Fragility of Contribution Score Computation in Federated Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pejo, Balazs, Frank, Marcell, Varga, Krisztian, Veliczky, Peter, Biczok, Gergely
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909870601535488
author Pejo, Balazs
Frank, Marcell
Varga, Krisztian
Veliczky, Peter
Biczok, Gergely
author_facet Pejo, Balazs
Frank, Marcell
Varga, Krisztian
Veliczky, Peter
Biczok, Gergely
contents This paper investigates the fragility of contribution evaluation in federated learning, a critical mechanism for ensuring fairness and incentivizing participation. We argue that contribution scores are susceptible to significant distortions from two fundamental perspectives: architectural sensitivity and intentional manipulation. First, we explore how different model aggregation methods impact these scores. While most research assumes a basic averaging approach, we demonstrate that advanced techniques, including those designed to handle unreliable or diverse clients, can unintentionally yet significantly alter the final scores. Second, we explore vulnerabilities posed by poisoning attacks, where malicious participants strategically manipulate their model updates to inflate their own contribution scores or reduce the importance of other participants. Through extensive experiments across diverse datasets and model architectures, implemented within the Flower framework, we rigorously show that both the choice of aggregation method and the presence of attackers are potent vectors for distorting contribution scores, highlighting a critical need for more robust evaluation schemes.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19921
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the Fragility of Contribution Score Computation in Federated Learning
Pejo, Balazs
Frank, Marcell
Varga, Krisztian
Veliczky, Peter
Biczok, Gergely
Machine Learning
Cryptography and Security
Computer Science and Game Theory
This paper investigates the fragility of contribution evaluation in federated learning, a critical mechanism for ensuring fairness and incentivizing participation. We argue that contribution scores are susceptible to significant distortions from two fundamental perspectives: architectural sensitivity and intentional manipulation. First, we explore how different model aggregation methods impact these scores. While most research assumes a basic averaging approach, we demonstrate that advanced techniques, including those designed to handle unreliable or diverse clients, can unintentionally yet significantly alter the final scores. Second, we explore vulnerabilities posed by poisoning attacks, where malicious participants strategically manipulate their model updates to inflate their own contribution scores or reduce the importance of other participants. Through extensive experiments across diverse datasets and model architectures, implemented within the Flower framework, we rigorously show that both the choice of aggregation method and the presence of attackers are potent vectors for distorting contribution scores, highlighting a critical need for more robust evaluation schemes.
title On the Fragility of Contribution Score Computation in Federated Learning
topic Machine Learning
Cryptography and Security
Computer Science and Game Theory
url https://arxiv.org/abs/2509.19921