MétaCan
Menu
← Back to cohort

Breaking Robustness: Free-Rider Attacks Against Contribution Evaluation in Federated Learning

2025· article· W7125594490 on OpenAlexaff
Sophia Haoran Chen, Kaiyu Li, Na Ta, Yong Wang

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsWilfrid Laurier University
Fundersnot available
KeywordsFederated learningVulnerability (computing)Class (philosophy)Mechanism (biology)Empirical researchTraining set

Abstract

fetched live from OpenAlex

Federated Learning (FL) enables privacy-preserving collaborative model training across multiple clients, with recent efforts increasingly focused on integrating contribution evaluation methods into its framework, which not only quantifies each client's contribution but also serves as a defence mechanism against malicious behaviour. While existing FL contribution evaluation techniques have proven effective in detecting attacks like label flipping or data replication, we identify a critical gap: they are vulnerable to strategically designed free-rider attacks that mimic positively contributive behaviours. In this paper, we propose GradPred, a novel free-rider attack framework that leverages time-series prediction to forecast future global gradient updates of the FL model, based on past gradient updates. This allows a malicious client to entirely bypass local training while still appearing to make meaningful contributions to the FL system, making the attack difficult to detect using state-of-the-art FL contribution evaluation methods. Through empirical evaluation, we reveal an overlooked aspect of vulnerability in FL and call for further investigation into detecting and defending against this class of stealthy, fine-grained free-rider attacks.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.019
metaresearch head score (Gemma)0.060
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.019
Threshold uncertainty score0.099

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0190.060
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0010.001
Science and technology studies0.0020.003
Scholarly communication0.0030.007
Open science0.0030.007
Research integrity0.0030.005
Insufficient payload (model declined to judge)0.0010.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.032
GPT teacher head0.313
Teacher spread0.282 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicPrivacy-Preserving Technologies in Data→French-language works237,207→