Skip to content

A Nesterov-Accelerated Byzantine-Robust Federated Learning

Nov 2025 · 1 citation · 58 references
Computer Science

TL;DR

Byrd-NAFL seamlessly integrates Nesterov's momentum into the federated learning process alongside Byzantine-resilient aggregation rules to achieve fast and safe convergence against gradient corruption.

Abstract

We investigate robust federated learning, where a group of workers collaboratively train a shared model under the orchestration of a central server in the presence of Byzantine adversaries capable of arbitrary and potentially malicious behaviors. To simultaneously enhance communication efficiency and resilience against such adversaries, we propose a Byzantine-resilient Nesterov-accelerated federated learning (Byrd-NAFL) algorithm. Byrd-NAFL seamlessly integrates Nesterov's momentum into the federated learning process alongside Byzantine-resilient aggregation rules to achieve fast and safe convergence against gradient corruption. We establish a finite-time convergence guarantee for Byrd-NAFL under non-convex and smooth loss functions with relaxed assumptions on the aggregated gradients. Extensive numerical experiments validate the effectiveness of Byrd-NAFL and demonstrate the superiority over existing benchmarks in terms of convergence speed, accuracy, and resilience to diverse malicious attacks.

View source

Similar papers

Open access Aug 2026

A Byzantine-Resilient Federated Learning Framework with Cryptographic Gradient Attestation Against Coordinated Model Poisoning Attacks

FedSentinel is presented, a novel Byzantine-resilient federated learning framework that combines cryptographic gradient attestation with adaptive trust-weighted aggregation to protect against coordinated model-poisoning attacks, which are among the most serious challenges.

Abdullah Abdulkarim Alnajim · 0 citations
#federated learning Open access Sep 2026

RetFL: a privacy-preserving and traceable framework for robust federated learning

RetFL is proposed, a CKKS-enabled robust aggregation framework for DFL that establishes a decentralized training workflow with VRF-based candidate selection and view change, and designs a weighted aggregation scheme that incorporates cosine similarity and a dynamic reputation mechanism to weight updates and suppress pe...

Yi-Cheng Huang, Zhou Zhou, You-Liang Tian et al. · 0 citations
Conference Open access Aug 2026

Model-Consistent Byzantine-Resilient Decentralized Federated Learning for Collaborative Missions

DFL-C is introduced, a novel Byzantine-resilient DFL architecture that enables decentralized nodes to perform collaborative training with global model consistency and implements a dual-domain trust scoring mechanism to provide resilience against data-domain Byzantine manipulations including model poisoning attacks.

Yue Li, Sudip Bhujel, Cameron Lira et al. · 1 citation
Sep 2026

ZMASA: Robust Aggregation for Federated Learning Against Byzantine Attacks.

A theoretical analysis showing that, under bounded retained residuals, the aggregation error is controlled by the candidate-set Byzantine contamination, the magnitude of retained Byzantine residuals, and the stability of attention weights, achieves competitive or superior robustness compared with classical and recent r...

Shu-Juan Tian, Shu-Huan Xiang, Gang Liu et al. · 0 citations
Preprint Aug 2026

BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning

BackDFL is presented, a unified benchmark for systematically evaluating DFL under realistic and adaptive backdoor attacks, and demonstrates that both state-of-the-art Byzantine-robust DFL methods and adapted FL backdoor defenses fail under modest malicious participation rates, especially in heterogeneous settings.

M. Bouchiha, Gregory Blanc, Yu-Fei Han · 0 citations

Related blog posts

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.