Newest papers

Privacy-Preserving Personalized Federated Learning (PPP-FL) for Medical Imaging

Md Morshedul Islam, Hossain Shahriar, Alfredo Cuzzocrea · 2026 · arXiv

DOI: 10.48550/arXiv.2610.27470 · open-access PDF

Portuguese

O aprendizado federado (FL) é um paradigma de aprendizado de máquina distribuído que reduz os custos de transmissão, atenua as restrições de compartilhamento de dados transfronteiriço e melhora a privacidade mantendo dados brutos em dispositivos locais. Os clientes em sistemas FL treinam modelos locais e compartilham apenas atualizações, que são agregadas por um servidor central. Enquanto esta configuração limita a exposição direta a dados, o FL permanece vulnerável a ataques de privacidade.

Machine translation (Meta M2M100); the English original follows.

Abstract

Federated learning (FL) is a distributed machine learning paradigm that reduces transmission costs, mitigates cross-border data sharing restrictions, and enhances privacy by keeping raw data on local devices. Clients in FL systems train local models and share only updates, which are aggregated by a central server. While this setup limits direct data exposure, FL remains vulnerable to privacy attacks. Existing attack and defense strategies have largely been developed for centralized systems, and adapting them to FL introduces new challenges due to its unique architecture and training workflow.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange