Biography

I am the research lead at Parameter Lab in Tübingen, Germany. My research interests lie in trustworthy AI, including adversarial machine learning, privacy, alignment, and uncertainty.

I hold a PhD degree in computer science from the University of Luxembourg. My PhD thesis focuses on analyzing the transferability of adversarial examples from the surrogate weight space of DNNs. I am a data scientist who graduated from Ensae ParisTech and a statistician who graduated from Toulouse School of Economics.

• Social Science Is Necessary for Operationalizing Socially Responsible Foundation Models

  Details PDF Poster

• Testing Uniform Random Samplers: Methods, Datasets and Protocols

  Details PDF

• Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models

  Details PDF Code Dataset Poster

• Calibrating Large Language Models Using Their Generations Only

  Details PDF Slides Code Poster Models

• TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification

  Details PDF Slides Video Code Poster

• ProPILE: Probing Privacy Leakage in Large Language Models

  Details PDF Slides Video Poster

• What Matters in Model Training to Transfer Adversarial Examples

  Details PDF Slides Video

• Going Further: Flatness at the Rescue of Early Stopping for Adversarial Example Transferability

  Details PDF Code

• LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity

  Details PDF Slides Video Code Poster

• Efficient and Transferable Adversarial Examples from Bayesian Neural Networks

  Details PDF Code Poster

Significant Contributions

• Adversarial Robustness Toolbox (ART)
• Torchattacks
• Implementation of state-of-the-art predictors for Spatial Regression Models in the spdep R package
• Integration of sentences in French into Common Voice (epub parsing and cleaning)

Minor Contributions

• huggingface/transformers
• scikit-learn
• GCG (LLM jailbreaking attack)
• piwik-log-analytics
• xtable
• hugo-academic
• share-on-diaspora
• framadate
• scrumblr
• ethercalc

2023 & 2024

Master: Erasmus Mundus Joint Master in Cybersecurity

The Erasmus Mundus Joint Master in cybersecurity (CYBERUS) at the University of Luxembourg. One session about adversarial examples against LLMs.

• Slides.
• Notebook showcasing jailbreaking: Google Colab, ipynb file.

2022

Master: Advanced topics in Applied Machine Learning

2nd year of Master in Computer Science. Two lectures, design and correction of the project, planning.

1. Recalls of machine learning, machine learning frameworks, first part project
2. Overview of adversarial machine learning, model calibration

Project: Creation and evaluation of fill-in-the-blank notebooks (part 1 on preprocessing and part 3 on adversarial examples)

Master: Introduction to Machine Learning

2nd year of Master in Space Science. Six sessions, including four based on the Machine Learning Refined book and one based on the Applied Machine Learning course of Andreas C. Müller. Summary slides.

1. Recalls of linear algebra: “Machine Learning Refined” book, “Essence of linear algebra” videos serie of 3blue1brown, some formal definitions from the “Mathematics for Machine Learning” book.
2. Zero-order optimization: Chapter 2, Appendix B.
3. First-order optimization: Chapter 3, “Gradient descent, how neural networks learn” video from 3Blue1Brown.
4. Linear regression and linear classification: Chapters 5 and 6
5. ML project lifecycle: Data preparation, feature engineering, overfitting & underfitting, model evaluation. Slides.
6. Neural Networks (slides), Keras & Convolutional Neural Nets (slides) and Advanced Neural Networks (slides).
7. Written examination

2021

Master: Introduction to Machine Learning

2nd year of Master in Space Science. Two introductory lectures on Machine Learning. Slides.

2020

Bachelor: Software engineering 2

3rd year of Bachelor in Computer Science. Four introductory lectures on Machine Learning Engineering. Course given online during lockdown. Quizzes on Moodle. Videos, Slides

1. Introduction to Machine Learning: Useful Definitions, Types of Tasks in Machine Learning
2. Introduction to Machine Learning: Recalls of Statistics, Model’s elements, Elements of Statistical Learning Theory
3. Machine Learning Project Lifecycle: When to (not) use Machine Learning, Goal Definition, Data Collection & Preparation
4. Machine Learning Project Lifecycle: Feature Engineering, Choosing and Training a model, Model Evaluation, Feedback loop

I served as a reviewer for the following conferences and journals.

Machine Learning Venues

• UAI 2024
• International Journal of Computer Vision
• IEEE Transactions on Neural Networks and Learning Systems
• IEEE Transactions on Pattern Analysis and Machine Intelligence
• UAI 2023
• SiMLA Workshop 2023

ML Reading Group

I organized and animated the weekly Machine Learning Reading Group at the SerVal group (University of Luxembourg) from February 2021 to August 2023.

Vulnerabilities discovered:

Contact me preferably by email and follow me on Twitter, Bluesky or Mastodon.

• martin at gubri dot eu