Skip to content
AI News HubLIVE
Original source2 min read

FedSharp: Byzantine Robust Decentralized Federated Learning Under Noisy Channel

Summary

The paper proposes FedSharp, a robust decentralized federated learning framework that addresses data heterogeneity, Byzantine attacks, and channel noise. By screening suspicious models, averaging the lowest-loss candidates, and applying noise-adaptive regularization, FedSharp achieves 93.5-94.9% accuracy on MNIST with 33 Byzantine nodes, far surpassing benchmarks.

SourcearXiv Machine LearningAuthor: Ojaswi Sinha, Amin Farajzadeh, Animesh Yadav, Melike Erol-Kantarci
FedSharp: Byzantine Robust Decentralized Federated Learning Under Noisy Channel
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 3 Nov 2026]

Title:FedSharp: Byzantine Robust Decentralized Federated Learning Under Noisy Channel

View a PDF of the paper titled FedSharp: Byzantine Robust Decentralized Federated Learning Under Noisy Channel, by Ojaswi Sinha and 3 other authors

View PDF HTML (experimental)

Abstract:Decentralized federated learning (DFL) eliminates the central aggregation server but remains vulnerable to data heterogeneity, Byzantine attacks, and channel noise. We show that noise accumulates as models propagate across nodes, becoming increasingly significant as the learning rate decays. Moreover, accumulated noise enables Byzantine attackers to exploit loss-based model selection by mimicking honest model averages. To address these challenges, we propose screened, hop-aware, ranked, proximal averaging, a robust DFL framework (FedSharp). In this approach, each node maintains models from its 2b predecessors, ensuring at least b honest candidates when at most b nodes are Byzantine. FedSharp screens suspicious models using coordinate-wise median deviations, averages the b lowest-loss candidates to reduce fresh channel-noise variance by a factor of b, and applies noise-adaptive gradient-norm regularization and proximal training to mitigate accumulated noise and non-IID drift. Experiments on a 100-node ring with 33 Byzantine nodes show that FedSharp achieves 93.5-94.9% accuracy on MNIST, compared with 29.4-38.1% for a state-of-the-art single-model-selection benchmark, and 32.8-48.8% on CIFAR-10, compared with 10.0-30.5%, across Gaussian and hidden attacks under IID and non-IID data. On MNIST, FedSharp also achieves accuracy within approximately one percentage point of the benchmark operating without channel noise.

Comments: 6 pages, 4 figures, submitted for possible publication

Subjects:

Machine Learning (cs.LG)

Cite as: arXiv:2611.05546 [cs.LG]

(or arXiv:2611.05546v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2611.05546

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Animesh Yadav [view email] [v1] Tue, 3 Nov 2026 19:37:46 UTC (576 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled FedSharp: Byzantine Robust Decentralized Federated Learning Under Noisy Channel, by Ojaswi Sinha and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.LG

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

ResearchersAdvanced

Key points

  • FedSharp maintains models from 2b predecessors to ensure at least b honest candidates under up to b Byzantine nodes.
  • It uses coordinate-wise median deviations for screening and averages the b lowest-loss models to reduce noise variance by a factor of b.
  • Experiments on a 100-node ring with 33 Byzantine nodes show 93.5-94.9% accuracy on MNIST versus 29.4-38.1% for a state-of-the-art benchmark.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Research