le 5 novembre 2025 à 13:30
Nicolas Papernot will give a seminar for M1 and M2 students in the Master’s programme in Data Science. It will take place at the Amphi Goubet lecture theatre at Centrale on 6 November 2025 at 1.30pm.
The talk presents open problems in the study of machine unlearning. The need for machine unlearning, i.e., obtaining a model one would get without training on a subset of data, arises from privacy legislation and as a potential solution to data poisoning or copyright claims. The first part of the talk discusses approaches that provide exact unlearning: these approaches output the same distribution of models as would have been obtained by training without the subset of data to be unlearned in the first place. While such approaches can be computationally expensive, we discuss why it is difficult to relax the guarantee they provide to pave the way for more efficient approaches. The second part of the talk asks if we can verify unlearning. Here we show how an entity can claim plausible deniability when challenged about an unlearning request that was claimed to be processed, and conclude that at the level of model weights, being unlearnt is not always a well-defined property. Instead, unlearning is an algorithmic property.
Lien visio : https://univ-lille-fr.zoom.us/j/93945435789?pwd=5seOvoACa3N4x9hwhQwTua8Lu3Ip1k.1
En savoir plus...Amphi Goubet at Centrale
français
English