Flavio Hafner

5 posts

Research Software Engineer working on privacy-preserving machine learning and statistical methods.

Differential Privacy3 Machine Learning3 Privacy3 Statistics3 Testing2 Databases2 Health1 Performance1

Jun 27, 2025

Empirically evaluating privacy in machine learning I: Introduction

Research in the social and health sciences often relies on accessing data sourced from statistical agencies or healthcare organizations. Such data sets contain sensitive information, which requires re...

Jun 17, 2025

Empirically evaluating privacy in machine learning II: Hypothesis testing

Using statistics to think like a hacker, so we can avoid them! Image from page 182 of “Elements of statistics” (1954). Licensed under creative commons.This post is the second in a series on evaluating...

Jun 17, 2025

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

1 Using statistics to think like a hacker, so we can avoid them! The Greek letter lambda, symbol of functional programming.This post is the third in a series on differential privacy and machine learni...

May 6, 2025

Benchmarking LLM fine-tuning on different HPC systems

43 > Authors: Flavio Hafner (Netherlands eScience center), Mattie Niznik (Princeton Research Computing), Malte Lüken (Netherlands eScience center), Alessandra Maranca (Princeton University), Matthew S...

Feb 27, 2024

How to manage your IP address in Python

> This post is the first of a series of blog posts arising from a collaboration between the eScience Center and the ODISSEI Social Data Science Team. You can find this text also at https://odissei-sod...