machine learning

FOSDEM 2026 highlights: security, LLMs, and software performance

Highlights and notes from FOSDEM 2026.

Empirically evaluating privacy in machine learning III: functional & gaussian differential privacy

The third in a series of blog posts on machine learning and privacy: why functional differential privacy is useful for auditing privacy in machine learning.

Empirically evaluating privacy in machine learning II: Hypothesis testing

The second in a series of blog posts on machine learning and privacy: Using statistics to think like a hacker, so we can avoid them!

Empirically evaluating privacy in machine learning I: Introduction

The first in a series of blog posts on machine learning and privacy.

Representation learning on population registry data

Training vector representations on Dutch registry data.

Empirical Privacy Evaluations of Generative and Predictive Machine Learning Models -- A review and challenges for practice

We review the empirical testing of privacy in machine learning. We discuss whether and how these tests could be used when evaluating generative algorithms for deployment at statistical agencies and in the health care system.