This site loads optional analytics from Google and external analytics providers only if you accept. You can decline and continue using the site normally.
Robust, explainable and privacy-aware machine learning systems for distributed and adversarial security settings.
Trustworthy AI is not a single metric. In security-sensitive systems it combines robustness, explainability, privacy, accountability and evidence that a model behaves acceptably under operational stress.
Distributed AI systems inherit all the usual machine learning risks and add communication constraints, partial observability, heterogeneous peers and inconsistent incentives. Trustworthy design must address the model, the protocol and the operational context together.
The related publications and projects approach trustworthy AI through robust aggregation, decentralized protocols, privacy-preserving learning, explainable mitigation support and evaluation in cyberdefense scenarios.
A trustworthy AI system is robust, explainable, privacy-aware, auditable and evaluated under conditions close to the environment where it will be used.
No. Explainability is important, but it must be combined with robustness, privacy, evaluation, governance and operational controls.
Federated systems rely on multiple clients and shared updates. Trustworthy design helps detect unreliable contributions, protect sensitive information and keep collaborative learning useful.
DEFENDIS develops a framework for uniquely identifying IoT devices in a distributed manner while solving security threats through decentralized federated learning.
View ProjectROBUST-6G studies security mechanisms for 6G systems, including monitoring, secure data management, trustworthy AI services, federated learning, and threat response.
View ProjectA project with armasuisse Cyber-Defence Campus investigating trustworthy threat intelligence sharing and verification algorithms.
View ProjectDeveloped decentralized AI solutions addressing computational constraints and trust validation under armasuisse Cyber-Defence Campus sponsorship.
View ProjectA measured research agenda for dynamic topologies, manipulated context, formal privacy analysis and external validity in robust DFL.
A practical map of LLM roles in cyberdefense, from threat-intelligence support to alert triage and explanation, with explicit limits and controls.
How to frame autonomous cyberdefense as a bounded control loop with evidence, policies, recovery paths and accountable human intervention.
A design pattern for using language models to explain incidents and compare mitigation options while approved policies retain control of execution.
An original guide to Parametric RAG, its promise for repeated domain knowledge and the evaluation questions raised by changing the model memory itself.