federated learning

Béton Roman Augmenté et Architecture Décentralisée

Résumé FRCe document, produit avec l’assistance de Gemini 3 Raisonnement, est publié sous licence Apache 2.0. Il constitue une publication défensive volontaire (antériorité) et entre de ce fait dans l’état de la technique au sens des législations applicables : art. 54(2) CBE (Convention sur le brevet européen), art. L...

Hyper-Personalization vs. Privacy Paradox: Balancing AI-Driven Customer Insights with Consumer Data Ethics and Trust

Abstract: The rapid proliferation of artificial intelligence and machine learning has enabled organizations to achieve unprecedented levels of hyper-personalization, transforming how brands interact with consumers. However, this capability intensifies the privacy paradox, a phenomenon where consumers express profound c...

Hyper-Personalization vs. Privacy Paradox: Balancing AI-Driven Customer Insights with Consumer Data Ethics and Trust

Abstract: The rapid proliferation of artificial intelligence and machine learning has enabled organizations to achieve unprecedented levels of hyper-personalization, transforming how brands interact with consumers. However, this capability intensifies the privacy paradox, a phenomenon where consumers express profound c...

Federated Machine Learning for Privacy-Preserving Intelligent Systems

Federated Machine Learning for Privacy-Preserving Intelligent Systems

FedTrust-GNN: Federated Learning with Blockchain Trust and Graph Neural Networks for Decentralized Modeling

Centralized user modeling systems inherently violate privacy regulations, with catastrophic failure points, opaque trust management mechanisms, and vulnerability to complex adversarial strategies such as poisoning attacks, model inversions, and membership inference. Federated learning (FL) approaches address data priva...

FedTrust-GNN: Federated Learning with Blockchain Trust and Graph Neural Networks for Decentralized Modeling

Centralized user modeling systems inherently violate privacy regulations, with catastrophic failure points, opaque trust management mechanisms, and vulnerability to complex adversarial strategies such as poisoning attacks, model inversions, and membership inference. Federated learning (FL) approaches address data priva...

Rapport Multidisciplinaire sur le Revenu Universel

Abstract ENThis document, produced with the assistance of ChatGPT o3 and ChatGPT 5 Thinking, is released under the Apache 2.0 licence. It is a voluntary defensive publication (prior art) and therefore enters the prior art upon release under the applicable patent statutes: art. L 611-11 CPI (French Intellectual Property...

Distributed Machine Learning and Federated Edge Computing for IoT

The growing scale and heterogeneity of Internet of Things (IoT) environments are shifting machine learning (ML) from centralized cloud infrastructures toward distributed intelligence across the IoT–edge–cloud continuum [...]

VertiMosaic

A reproducible research framework for vertical federated learning on heterogeneous tabular data with explicit privacy boundaries, provenance and communication auditing.

FedPath-MTL: A Federated Multi-Task Framework for Personalized Learning Pathways with Real-Record Predictive Evaluation

Personalized learning pathways are difficult to support in distributed educational systems because learner records cannot always be centralized and one shared federated predictor may not represent heterogeneity across institutions, learning tasks, and individual learners. We propose FedPath-MTL, a federated multi-task...

Decentralized Gradient Verification in Federated Learning Via Recursive zk-SNARKs