federated learning

FedColMem-H: Communication-Neutral Decision-Head Personalization for Heterogeneous Federated Node Classification

Federated node classification is not easy when clients hold induced subgraphs with different class proportions and different local topology. Existing graph-specific approaches change aggregation, distillation or cross-client knowledge transfer, which can increase personalization but can also be associated with a differ...

Reproducibility package for "A Systematic Review of Robustness and Trustworthiness Evaluation in Federated IoT Intrusion Detection"

Search strings, screening decisions, included-study list (n = 70), coding decision log, differential-privacy audit and PRISMA 2020 checklist for a systematic review of federated learning-based intrusion detection in IoT.

Agentic AI-Based Medical Data Governance and Trust Management

Due to increasing reliance on cloud, distributed computing platforms, electronic health records (EHRs), Internet of Medical Things (IoMT), and other modern information systems, secure medical data governance has become increasingly difficult for healthcare companies.Dynamic trust evaluation, independent policy enforcem...

Developing Robust Federated Learning-Based Anomaly Detection Against Poisoning Attacks in 5G Networks

The rapid expansion of fifth-generation 5G wireless networks has significantly increased the attack surface available to adversaries who seek to disrupt critical communication infrastructure. Traditional centralized intrusion detection systems expose raw user data to a central server, creating unacceptable privacy risk...

ReSIDS: A Resilient, runtime-Switchable federated–gossip IDS for IEC 61850 Power Systems

ReSIDS / ereno-Adaptativo is an intrusion-detection pipeline that unifies centralized, federated and gossip learning in a single run with round-by-round mode switching, built on Flower, scikit-learn and XGBoost. This is the v1.x (Paper 1 / JPDC) lineage: per-attack XGBoost specialists with k-of-n decision fusion, runti...

Is Non-IID an Artifact of Training from Scratch? A Critical Review of Data Heterogeneity in Federated Learning in the Pretraining Era

THE EL-RAKHAWI THEORY OF QUANTUM-ARCHITECTURAL RESILIENCE AND URBAN NEURO-HARMONY Unifying Urban Neuroscience, Metamaterials, Environmental Law, and Predictive AI for Planetary Urban Healing

The El-Rakhawi Theory of Quantum-Architectural Resilience and Urban Neuro-Harmony (DOI: 10.5281/zenodo.23275573) reconceptualizes the city as an "external organ" of the human body. It unifies Urban Neuroscience, Metamaterials, Predictive AI, and Environmental Law to transform urban spaces into regenerative, healing eco...

Research data for Participation History and Deployment Readiness in Personalized Federated Learning

Federated Learning for Enterprise Cloud Data Engineering: Architecture, Security, and Governance Challenges

This research examines the application of federated learning in enterprise cloud environments, focusing on architecture, security, privacy preservation, and governance challenges. It explores how organizations can collaboratively train machine learning models across distributed datasets without centralizing raw data. T...

RFLDefense: robust federated learning defense against targeted attacks

Federated learning (FL) is a distributed machine learning framework that protects data privacy by allowing multiple participants to jointly train models without sharing local data. However, the distributed nature of FL systems makes them susceptible to backdoor attacks, where attackers inject malicious updates to disru...

Causality-driven hybrid intrusion detection with entropy-aware feature learning and federated intelligence

Modern IDSs should be capable of detecting and recognizing new forms of attack traffic (including both attacks from known adversaries) and to do so in ways that remain computational feasible when deployed across multiple, geographically distributed sites. Rule based, representation learning, and federated approaches ha...

An adaptive federated deep learning approach for efficient DDoS detection in IoT edge networks

Abstract The rapid growth of the Internet of Things (IoT) has expanded the attack surface of modern networks, motivating the need for accurate detection of DDoS and botnet activity in resource-constrained settings. Centralised intrusion detection systems (IDS) face privacy, scalability, and heterogeneity challenges tha...