6 papers
From Privacy to Trust in the Agentic Era: A Taxonomy of Challenges in Trustworthy Federated Learning Through the Lens of Trust Report 2.0
Nuria RodrÃguez-Barroso, Mario GarcÃa-Márquez, M. Victoria Luzón +1
Federated Learning (FL) enables privacy-preserving collaborative learning, yet deployments increasingly show that privacy guarantees alone do not sustain trust in high-risk setting…
Resilient Federated Chain: Transforming Blockchain Consensus into an Active Defense Layer for Federated Learning
Mario GarcÃa-Márquez, Nuria RodrÃguez-Barroso, M. Victoria Luzón +1
Federated Learning (FL) has emerged as a key paradigm for building Trustworthy AI systems by enabling privacy-preserving, decentralized model training. However, FL is highly suscep…
RAB-DEF: Dynamic and explainable defense against adversarial attacks in Federated Learning to fair poor clients
Nuria RodrÃguez-Barroso, M. Victoria Luzón, Francisco Herrera
At the same time that artificial intelligence is becoming popular, concern and the need for regulation is growing, including among other requirements the data privacy. In this cont…
Improving -Byzantine Resilience in Federated Learning via layerwise aggregation and cosine distance
Mario GarcÃa-Márquez, Nuria RodrÃguez-Barroso, M. Victoria Luzón +1
The rapid development of artificial intelligence systems has amplified societal concerns regarding their usage, necessitating regulatory frameworks that encompass data privacy. Fed…
Membership Inference Attacks fueled by Few-Short Learning to detect privacy leakage tackling data integrity
Daniel Jiménez-López, Nuria RodrÃguez-Barroso, M. Victoria Luzón +1
Deep learning models have an intrinsic privacy issue as they memorize parts of their training data, creating a privacy leakage. Membership Inference Attacks (MIA) exploit it to obt…
Krum Federated Chain (KFC): Using blockchain to defend against adversarial attacks in Federated Learning
Mario GarcÃa-Márquez, Nuria RodrÃguez-Barroso, M. Victoria Luzón +1
Federated Learning presents a nascent approach to machine learning, enabling collaborative model training across decentralized devices while safeguarding data privacy. However, its…