Presenting Oblivious Audits at AIES26.

Mixing canaries, Private Information Retreival to make AI audits more robust against malicious providers. Come see the poster at AIES! project, arXiv

Joining MPI-SWS a postdoc!

With Manuel and team, expect some incentive modeling, human/AI/regulator cooperation, and much more.

Thinking Out of the (Black)-Box, PhDone.

Many thanks to my advisors, the jury, and everyone who came. defense page, manuscript

Our formalization of auditing with a prior has been accepted as spotlight paper at ICML25!

Learn more on the project page or the arXiv.

An ARTISHAU in Toronto.

Just arrived in Toronto where I will be a Visiting PhD Student in the CleverHans lab for six months. Exited to work on user audits with Mohammad and Nicolas, and to enjoy Toronto!

AAAI25, let's talk about model fingerprinting.

What started as a simple project on model distances became a full-fledged analysis of the model fingerprinting problem and its evaluation. ArXiv, code, poster

SaTML 2024: Under manipulations, are there models harder to audit?

Our results on the auditability of large models in the presence of platform manipulation have been accepted to SaTML 2024! paper, ArXiv, project

WIDE @ EPFL

I will be presenting our results on the auditability of large models in the presence of platform manipulation to the IC school at EPFL on Dec. 9th at 11AM. slides, poster

PFIA 2023: Change-Relaxed Active Fairness Auditing

I will be presenting an early version of our work on the black-box auditability of ML models at PFIA. You can find the paper here, more to come on that subject!

Journal publication of the reworked CNA 2021 study

Our work on the effect of collaborative filtering on the diversity of users’ exposure has been accepted for publication in Applied Network Science! More info here.

🥈 2nd place at PeREN hackathon with Jade!

The « Segmente moi si tu peux ! » hackathon, was organized by the PeREN. The goal was to detect the type of pricing algorithm behind a delivery app by generating black-box queries to the app. We reached the second place, together with Jade Garcia-Bourrée and were awarded our price by the French Minister for Digital Transition and Telecommunications Jean-Noël Barrot.

Off to Rennes!

I am starting my PhD on “Auditing the mutations of online AI models” at WIDE!

NLE internship

Grenoble, here I come! Starting my masters final internship at NaverLabs Europe with Jean-Michel Renders on Diversity in Search and Recommendation systems.

CNA 2021

I will be presenting our work “Recommender systems increase exposure diversity. Or do they? A complex networks approach., Augustin Godinot, Fabien Tarissan” at the Complex Networks and their Applications conference! Slides and info here.

Submitted our article to RecSys!

We submitted our Measuring the effect of collaborative filtering on the diversity of users’ attention article together with Fabien!

Created this website!