Decentralized Federated Learning
Peer-to-peer and semi-decentralized learning systems where nodes collaborate without relying on a single central server.
Explore topicFederated Learning · Trustworthy AI · Cyberdefense
Enrique Tomás Martínez Beltrán
PhD candidate at the University of Murcia working on federated learning for cybersecurity and cyberdefense, with a focus on distributed, privacy-preserving and robust learning systems.
7+
Applied research years
4
EU/defense programmes
PhD
University of Murcia PhD candidate
1300+
Citations
Location
Spain
Contact
enriquetomas@um.es
Academic & Professional Profiles
Ph.D. Researcher in Federated Learning and Cybersecurity
Academic and professional profiles to follow scientific output, research identity, and technical activity.
Research Interests
The main lines I am currently working around, with a focus on distributed learning and security.
LLMs for Cyberdefense Support
LLMs used as a support layer to explain what is happening, compare mitigation options, and keep the analyst in the loop.
Explore topicTrustworthy AI
Evaluation of robustness, explainability, accountability and reliability in machine learning systems used in security-sensitive settings.
Explore topicAI and Machine Learning for Cyberdefense
Machine learning applied to incident management, threat detection, IoT security and critical infrastructure monitoring.
Explore topicResearch Activity
A short overview of my research output, funded project experience, public academic profiles, and applied work across cybersecurity, cyberdefense, and distributed AI.
1300+
citations
Public scholarly footprint based on Google Scholar metadata available in the repository.
4
EU/defense programmes
Work connected to European, defense, IoT security, emergency systems, and BCI security research contexts.
7+
applied research years
Work across distributed AI, cybersecurity, and privacy-preserving systems.
8
public profiles
GitHub, LinkedIn, Scholar, ORCID, Scopus, DBLP, Web of Science, and ResearchGate.
Selected Research Projects
Projects where I have worked on federated learning, distributed AI, security monitoring, cyberdefense, 6G security and resilient systems.
Apr 2023 — Nov 2023Completed
DEFENDIS: Decentralized Federated Learning for IoT Device Identification and Security
DEFENDIS develops a framework for uniquely identifying IoT devices in a distributed manner while solving security threats through decentralized federated learning.
Security problemIoT deployments need device identity mechanisms that remain useful when central services are unavailable, compromised, or unsuitable for sensitive telemetry.
Decentralized Federated LearningAdversarial MLIoT SecurityCybersecurityTrustworthy AI
View Project
Dec 2022 — Nov 2025Completed
EU-GUARDIAN: European Framework and Proofs-of-concept for the Intelligent Automation of Cyber Defence Incident Management
A European research project on methods and proofs of concept for supporting cyber defence incident management.
AICyberdefenseAutomation
View ProjectRecent Publications
Selected highlights from research in federated learning, distributed AI, communications security, trustworthy AI and cybersecurity.
Journal article2026
Computer Networks
Asynchronous Cache-based Aggregation with Fairness and Filtering for Decentralized Federated Learning
Enrique Tomás Martínez Beltrán, Eduard Gash, Gérôme Bovet, Alberto Huertas Celdrán, Burkhard Stiller
Decentralized Federated Learning (DFL) offers a scalable paradigm for collaborative intelligence at the edge, yet its practical efficacy is severely constrained by system heterogeneity. Traditional synchronous protocols...
Journal article2026
Information Fusion
Decentralized Federated Learning with Multimodal Prototypes for Heterogeneous Data
Enrique Tomás Martínez Beltrán, Gérôme Bovet, Gregorio Martínez Pérez, Alberto Huertas Celdrán
Preprint2026
Submitted to Future Generation Computer Systems
Decentralized Self-Supervised Representation Learning via Prototype Exchange under Non-IID Data
Enrique Tomás Martínez Beltrán, Gérôme Bovet, Gregorio Martínez Pérez, Alberto Huertas Celdrán
Journal article2026
Future Generation Computer Systems
FedEnD: Communication-efficient Federated Learning for non-IID data via decentralized ensemble distillation
Enrique Tomás Martínez Beltrán, Philip Giryes, Gérôme Bovet, Burkhard Stiller, Gregorio Martínez Pérez, Alberto Huertas Celdrán
Federated Learning (FL) offers a paradigm for collaborative AI that mitigates raw data exposure, yet the statistical heterogeneity of client data severely constrains its practical application. This non-independent and id...
Conference paper2026
XI Jornadas Nacionales de Investigación en Ciberseguridad (JNIC 2026)
MadHoney: Señuelos Tóxicos para la Defensa Activa en el Aprendizaje Federado Descentralizado
Pedro Beltrán López, Enrique Tomás Martínez Beltrán, Pantaleone Nespoli, Manuel Gil Pérez, Gregorio Martínez Pérez, Alberto Huertas Celdrán
Research Notes
Notes on federated learning, decentralized AI, threat detection, explainability, applied cybersecurity, and occasional work with LLMs.
NEWMay 30, 20261 day ago·8 min read
From Monitoring to Mitigation: A DFL Cyberdefense Lifecycle with LLM Explanations
A practical note on how distributed monitoring, DFL models, alert evidence and LLM-based support can fit into a cyberdefense workflow.
Decentralized Federated LearningLLMsExplainable AIAttack MitigationCyberdefense
Read More
NEWMay 29, 20262 days ago·7 min read
Situational Awareness for Cyberdefense with Decentralized Federated Learning
A research note on using DFL to turn distributed telemetry, anomalies and trust signals into cyberdefense situational awareness.
Situational AwarenessDecentralized Federated LearningExplainable AICyberdefense
Read More