Biography

Martin Gubri is a PhD candidate at SnT center, University of Luxembourg. His research interests are in Machine Learning Security, focusing on probabilistic perspectives of adversarial attacks.

He is a Data Scientist graduated from Ensae ParisTech and a Statistician graduated from Toulouse School of Economics.

He has developed a personal interest for Security, leading to the discovery of several FLOSS vulnerabilities.

• 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

• Influence-driven data poisoning in graph-based semi-supervised classifiers

  Details PDF Slides Code

• Search-Based Adversarial Testing and Improvement of Constrained Credit Scoring Systems

  Details PDF Slides Video Code

• Adversarial perturbation intensity strategy achieving chosen intra-technique transferability level for logistic regression

  Details PDF Code

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

• scikit-learn
• piwik-log-analytics
• xtable
• hugo-academic
• share-on-diaspora
• framadate
• scrumblr
• ethercalc

2022

Master: Advanced topics in Applied Machine Learning

2nd year of Master in Computer Science. Two lectures, project, planning.

1. Recalls of machine learning, machine learning frameworks, first part project
2. Overwiew 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

• SiMLA workshop 2023
• IJCAI 2023
• UAI 2023
• CVPR 2023
• NeurIPS 2022 (Datasets and Benchmarks Track)
• IEEE Transactions on Image Processing (Journal)
• AAAI 2021
• AAAI 2022

Software Engineering Venues

• ICSE 2021
• ICSE 2022
• FSE 2020
• FSE 2022
• ICST 2020
• ICST 2021
• QRS 2020
• QRS 2022
• SANER 2023

ML Reading Group

I organize and animate the weekly Machine Learning Reading Group at the SerVal group (University of Luxembourg) since February 2021.

Vulnerabilities discovered:

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

• martin at gubri dot eu