federated learning

AI-Standardized Secure Digital Twins for Smart Home Ecosystems

Digital Twins (DTs) are emerging as foundational components of next-generation communication systems, offering real-time synchronization, predictive modeling, and autonomous control across consumer electronics. However, their integration with AI/ML, edge–cloud infrastructures, and 5G/6G networks significantly enlarges...

Expert-wise federated learning with sparse routing for distributed traffic prediction

DPArena: A platform for reproducible experiments on data poisoning in federated learning

EDAF: An Enhanced Dual-Alignment Framework for Robust Federated Learning in Heterogeneous IoT Environments

Federated learning (FL) in real-world deployments is fundamentally challenged by heterogeneous environments, where clients differ in both model architectures and computational capacities (system heterogeneity), as well as in local data distributions (statistical heterogeneity due to nonindependent and nonidentically di...

Long-Term Optimal Incentives for Differential-Privacy Federated Learning: A Multi-Stage Game Approach

Differential-privacy federated learning (DP-FL) has emerged as a promising paradigm capable of mitigating the inherent threat of traditional FL architectures that are vulnerable to inferential attacks due to the frequent exchange and updating of model parameters. However, existing DP-FL frameworks often assume that the...

Federated Learning on the American Science Cloud using APPFL

It is argued that offering federated computing as an important AmSC service would unlock privacy-constrained scientific collaborations, enabling public-private partnerships in model building while exercising and enhancing the platform's own federated infrastructure.

Blockchain-Enabled Artificial Intelligence and AI Agents for Secure Data Sharing and Cybersecurity Applications

This paper presents a meta-synthesis that draws together four constituent studies covering adversarial machine learning, AI-powered anomaly detection in cloud environments, automated vulnerability patching by multi-agent large language model (LLM) pipelines, and the broader landscape of securing AI systems across their...

Decentralized Federated Learning with Byzantine Fault Tolerance using Graph Neural Networks

Federated learning (FL) offers a promising approach to training machine learning models on decentralized data without directly exchanging the data itself. However, FL systems are vulnerable to Byzantine attacks, where malicious participants introduce corrupted data or models to compromise the learning process. This pap...

Fedflow: cloud orchestration for federated learning with the FeatureCloud platform

fedflow, a Python-based command-line tool for headless orchestration of FL tasks with FeatureCloud, is introduced, a Python-based command-line tool for headless orchestration of FL tasks with FeatureCloud that enables automation of multi-client FL tasks, facilitates embedding of FeatureCloud in standard bioinformatics...

Decentralized Federated Learning with Differential Privacy

Federated learning (FL) offers a promising paradigm for training machine learning models on decentralized data sources without directly exchanging data. However, traditional FL approaches often struggle with data heterogeneity, communication bottlenecks, and, crucially, privacy concerns. This paper proposes a novel dec...

Wisdom contiuum

The Wisdom Continuum: A Unified Theory of Human Development, Learning, Intelligence, Artificial Intelligence, and Civilizational Evolution Description / Abstract The Wisdom Continuum presents a civilizational-scale framework that unifies human development, moral philosophy, educational reform, and artificial intelligen...

Decentralized Federated Learning with Differential Privacy

Federated learning (FL) offers a promising paradigm for training machine learning models on decentralized data sources without directly exchanging data. However, traditional FL approaches often struggle with data heterogeneity, communication bottlenecks, and, crucially, privacy concerns. This paper proposes a novel dec...