4 papers
Model Multiplicity for Adversarial Detection in Small Language Model Training on Edge Devices
Stefan Behfar, Richard Mortier
The rise of edge-based machine learning has enabled distributed adaptation of language models across mobile and IoT devices, offering privacy preservation and real-time responsiven…
Robust Synchronisation for Federated Learning in The Face of Correlated Device Failure
Stefan Behfar, Richard Mortier
Probabilistic Synchronous Parallel (PSP) is a technique in distributed learning systems to reduce synchronization bottlenecks by sampling a subset of participating nodes per round.…
Towards Adaptive, Learning-Based Security in Decentralized Applications
Stefan Kambiz Behfar, Jon Crowcroft
Web3 systems expose a fundamentally different security landscape from centralized platforms, characterized by composability, pseudonymous identities, decentralized governance, and…
Cumulative Utility Parity for Fair Federated Learning under Intermittent Client Participation
Stefan Behfar, Richard Mortier
In real-world federated learning (FL) systems, client participation is intermittent, heterogeneous, and often correlated with data characteristics or resource constraints. Existing…