3 papers
cs.LG2026
DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning
Marc Molina Van den Bosch, Riccardo Taiello, Albert Sund Aillet +3
Differentially private optimization suffers from a fundamental geometric mismatch: deep networks have highly anisotropic loss landscapes, yet DP-SGD injects isotropic noise. Second…
cs.CV2026
Federated Transformer-GNN for Privacy-Preserving Brain Tumor Localization with Modality-Level Explainability
Andrea Protani, Riccardo Taiello, Marc Molina Van Den Bosch +1
Deep learning models for brain tumor analysis require large and diverse datasets that are often siloed across healthcare institutions due to privacy regulations. We present a feder…
cs.CV2026
Decoder-Free Supervoxel GNN for Accurate Brain-Tumor Localization in Multi-Modal MRI
Andrea Protani, Marc Molina Van Den Bosch, Lorenzo Giusti +6
Modern vision backbones for 3D medical imaging typically process dense voxel grids through parameter-heavy encoder-decoder structures, a design that allocates a significant portion…