Research. Protect. Collaborate.
University of Murcia
AI, cybersecurity and federated learning
I research at the intersection of artificial intelligence, cybersecurity and federated learning to build systems that detect threats, protect data and learn in a decentralized, trustworthy way.
Find publications, research identity and technical work across the main academic profiles.
AffiliationCyberDataLabopens in a new tab / University of Murciaopens in a new tab
Recent work on federated learning, cybersecurity and trustworthy AI, with a short note on why each contribution matters.
Journal article / Computer Networks / 2026
CAFF addresses delays and unequal participation in asynchronous DFL. A cache with one slot per neighbour, staleness filtering and an adaptive threshold balance training efficiency and predictive quality.
Journal article / Information Fusion / 2026
Modalis addresses clients with different or missing modalities in decentralized learning. It exchanges compact class prototypes and aligns local representations to support collaboration across heterogeneous data.
Preprint / Submitted to Future Generation Computer Systems / 2026
This manuscript studies self-supervised representation learning through prototype exchange between peers with non-IID data. It has been submitted to Future Generation Computer Systems.
Three projects linking distributed AI, cyberdefense and trustworthy security research across European and applied settings.
An architectural evolution of the European cyber situational awareness platform into a modular System of Systems to support military missions.
ROBUST-6G studies security mechanisms for 6G systems, including monitoring, secure data management, trustworthy AI services, federated learning, and threat response.
DEFENDIS develops a framework for uniquely identifying IoT devices in a distributed manner while solving security threats through decentralized federated learning.
Selected research notes and technical guides connecting federated learning, threat detection and cyberdefense workflows. The archive includes every note in publication order.
Connect telemetry, federated learning, alerts and LLM-assisted mitigation with traceable evidence, validation and reviewed feedback.
Build cyberdefense situational awareness with DFL: provenance, coverage, uncertainty and shared context for operational decisions.
This site loads optional analytics from Google and external analytics providers only if you accept. You can decline and continue using the site normally.
Contact
For research collaborations, European projects, invited talks or applied work in secure distributed AI, send a short note with the context.
enriquetomas@um.esA short context helps me route the message quickly. I usually reply within a few working days.