Marc Molina
Van den Bosch

ε = 0.10

Privacy Engineer & Machine Learning Researcher

Industrial PhD @ CERN × Universitat Pompeu Fabra · Geneva, Switzerland

About

I work on the part of machine learning where the guarantee matters as much as the accuracy: differential privacy, secure aggregation, and federated learning, composed into distributed-DP systems with end-to-end guarantees — plus second-order optimisation that recovers the utility DP-SGD gives away.

Alongside the theory, I ship: CAFEIN, CERN's federated learning platform; a synthetic-data pipeline hospitals actually share at Kantonsspital Aarau; and Kosmico, a collaborative AI-native research platform.

Based inGeneva, CH
PhDCERN × UPF
MScFHNW · Novartis Diplompreis
BScUPC — Biomedical Eng.
LanguagesEN · ES · CA
Research
Contact

Open to conversations about differential privacy, federated systems, and building things that protect the people in the data.

Building
Kosmico

Kosmico

A collaborative, AI-native research platform — built for how research actually gets done.

kosmico.ai ↗
Experience

Industrial PhD Researcher, Private & Federated ML

Apr 2025 — now

CERN × Universitat Pompeu Fabra · Geneva

Second-order methods for sample- and user-level DP. Distributed DP combining differential privacy, secure aggregation, and federated learning. CAFEIN platform.

Machine Learning Researcher

Feb 2024 — now

Kantonsspital Aarau · Aarau

Privacy-preserving synthetic image pipeline with multimodal conditioning for cross-hospital sharing; evaluation spanning quality, diversity, and memorisation.

Data Science Intern

Aug 2023 — Jan 2024

Roche · Basel / Kaiseraugst

Anomaly detection for large-scale clinical-trial wearable and observational data; LLM + RAG system on Azure for trial findings reporting.

Biomedical Computer Vision Developer

Jun 2021 — Aug 2023

Vall d'Hebron Research Institute · Barcelona

Graph U-Net on vessel graphs; cerebral artery and large-vessel-occlusion segmentation on CTA volumes for stroke workflows.

Publications & Awards
2026

The Missing Sampler: Distributed Privacy Accounting for Asynchronous Federated Learning

Under review · PDF ↓

NeurIPS
2026

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning

PDF ↓

ICML
2026

Architecture-Driven Preconditioning for Sample-Efficient Differentially Private Medical Image Segmentation

Under review

MICCAI
2025

The Interplay Between Explainability and Differential Privacy in Federated Healthcare

DECAF

MICCAI
2025

Decoder-Free Supervoxel GNN for Accurate Brain-Tumor Localization in Multi-Modal MRI

GRAIL

MICCAI
2024

Memorization Detection Benchmark for Generative Image Models

Safe Generative AI Workshop

NeurIPS
2024

Enhancing federated learning in multicenter studies via synthetic data generation for improved downstream performance

RSNA
2024

A multifaceted evaluation framework of generative medical image models

Best MSc thesis — Novartis Industry Diplompreis

Award
2024

Conditional Style-based GANs for Generating Synthetically Private Mammograms

Top-5 abstract — KSA Tag der Innovation & Forschung

Award
2024

Evolutionary, Bayesian, and Quasi-Monte Carlo Hyperparameter Tuning

ISBM
2023

Fully automated Large Vessel Occlusion localization and segmentation from CT and CTA

ESOC