Skip to content
#federated learning Open access

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

Sep 2026 · Journal of King Saud University: Computer and Information Sciences · Vol 38 · 0 citations · 37 references
Privacy-Preserving Technologies in Data

TL;DR

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 persistently malicious participants.

Abstract

Federated learning (FL) enables multiple clients to jointly train a model without sharing raw data. Decentralized federated learning (DFL) further removes the need for a trusted central coordinator in the aggregation process. However, in decentralized settings, model aggregation is vulnerable to inference and poisoning attacks, and achieving efficient and traceable training remains challenging. To address these challenges, we propose RetFL, a CKKS-enabled robust aggregation framework for DFL. Specifically, we establish a decentralized training workflow with VRF-based candidate selection and view change. Then, we design a weighted aggregation scheme that incorporates cosine similarity and a dynamic reputation mechanism to weight updates and suppress persistently malicious participants. Finally, we enable scalable encrypted aggregation by efficiently realizing normalization verification within CKKS. Experimental results indicate that RetFL maintains performance close to standard FL methods even under challenging adversarial conditions, while achieving better model quality than existing robust FL approaches under comparable robustness requirements.

Read PDF

Similar papers

#machine learning Preprint Sep 2026

End-to-End Verifiable and Robust Federated Learning

The results show that robust outlier exclusion and public verifiability can be jointly achieved in a federated learning setting.

Doryan Lesaignoux, Enrique Mármol Campos, Gabriele Spini 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
#federated learning Open access Sep 2026

Trustworthy and privacy-preserving decentralized federated learning with multi-layer defense for secure collaborative AI

These findings demonstrate that the proposed framework provides an effective balance between privacy preservation, adversarial robustness, and trustworthy decentralized collaborative learning for secure AI-driven systems.

Durga Sivan, Uma Maheshwari Shanmugam, Sachnev Vasily et al. · 0 citations
2026

Differential Privacy Enabled Cascaded Filter for Efficient and Privacy-Preserving Federated Learning

Federated learning (FL) enables collaborative model training across multiple clients in a privacy-preserving manner. However, the employment of homomorphic encryption algorithms might lead to high computational cost while the application of differential privacy (DP) methods would sacrifice model performance. To establi...

Zhiqiang Chen, Yuchen Jiang, Ray Y. Zhong et al. · 0 citations
Sep 2026

Graph-aware Byzantine-resilient aggregation for adaptive poisoning detection in federated learning

GRAB-FL is proposed, a graph-aware, Byzantine-resilient FL framework for a bounded gray-box setting in which adversaries may observe global model trajectories and adapt their updates over time but cannot inspect server-side trust states.

Salam Fraihat, Yousef K. Sanjalawe, Qussai M. Yaseen et al. · 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.