federated learning

Sharp Robust Aggregation in Federated and Distributed Learning: Exact Byzantine Robustness Coefficients, Interactive Communication Lower Bounds, and Compressed Delayed Momentum

This research release develops sharp mathematical results for Byzantine-robust aggregation, exact communication complexity, and compressed delayed momentum in federated and distributed optimization. The work studies a central question in robust distributed learning: how accurately can a server aggregate vectors when up...

A Review on Machine Unlearning Algorithms and Privacy Protection

The role of unlearning in privacy protection and its dual role in security is examined, where it serves as a defense against poisoning and backdoors but also becomes an attack surface and verifiable unlearning in federated and decentralized environments remains a central open problem.

DPPF: a decentralized privacy-preserved framework using blockchain and federated learning for IoT driven smart cities

Sharp Robust Aggregation in Federated and Distributed Learning: Exact Byzantine Robustness Coefficients, Interactive Communication Lower Bounds, and Compressed Delayed Momentum

This research release develops sharp mathematical results for Byzantine-robust aggregation, exact communication complexity, and compressed delayed momentum in federated and distributed optimization. The work studies a central question in robust distributed learning: how accurately can a server aggregate vectors when up...

Cloud Robotics and Edge Intelligence: Distributed Control, Latency Modeling, and Fleet Coordination

An open-access curriculum module exploring the architectural frameworks, communication bounds, and machine learning topologies that govern distributed robotics. Covers three-tier cyber-physical hierarchies (embedded edge devices, local fog/edge servers, centralized hyper-scale cloud), non-minimum phase transfer functio...

Cloud Robotics and Edge Intelligence: Distributed Control, Latency Modeling, and Fleet Coordination

An open-access curriculum module exploring the architectural frameworks, communication bounds, and machine learning topologies that govern distributed robotics. Covers three-tier cyber-physical hierarchies (embedded edge devices, local fog/edge servers, centralized hyper-scale cloud), non-minimum phase transfer functio...

FedMuse: A Privacy-Aware Federated Framework for Multi-Style Text-to-Image Art Generation

FedMuse is proposed, a privacy-aware federated framework for multi-style text-to-image art generation, in which distributed clients collaboratively train a shared generative model while keeping their private art data local, and an adaptive privacy regularizer is introduced to reduce memorization risk while maintaining...

Artificial Intelligence-Enabled Low-Carbon Transition in Shipping: A Systematic Bibliometric Review

An evidence-informed AI-to-Carbon Value Chain conceptual synthesis comprising data observability, model credibility, decision executability, system coordination, and carbon verification is advanced, although this synthesis is interpretive rather than a validated causal framework.

Heavy data and AI updates stay off-chain, while a permissioned blockchain stores critical proofs, identity, authorization, roaming records, slice events, and audit trails. This builds trust between operators and supports AI/federated learning. Main tradeoffs—latency, scalability, privacy, and decentralization—are handled with hybrid on/off-chain designs.

Deep Learning, Federated Learning, and Meta-Learning for Intrusion Detection in the Internet of Things: A Systematic Review, Taxonomy, and Research Agenda

Auditable update-utility certificates for personalized federated learning

Reliability metadata improve federated aggregation when they predict the value of a client update for other participants when they predict the value of a client update for other participants using auditable cross-client update-utility certificates.

HAFN: a federated learning framework for privacy-preserving stress detection

This study proposes a federated learning framework, the Hierarchical Attention Fusion Network (HAFN) combined with the FedNova aggregation strategy for privacy-preserving multimodal stress classification, and demonstrates robustness and effectiveness of the proposed framework.