State of the art - Preserving Privacy in Deep Learning Models

This state of the art will be led by Tom Sander, META AI (FAIR)

Deep Learning models are known for their capacity to memorize training data, a characteristic that can lead to significant privacy concerns.

In this talk, we will delve into the implications of this memorization and explore strategies to mitigate its effects. We will discuss practical methods to reduce unintended memorization and their results, providing insights into how these techniques can be deployed in real-world scenarios.

Tom’s work: https://scholar.google.com/citations?user=xrewx-sAAAAJ&hl=en

Détails: événement en anglais, en visio et en présentiel

Audience: technique

This event is reserved for our members, but we still have a few places available for those who would like to discover the club. Don't hesitate to register: You'll be put on a waiting list and we'll confirm your participation 3 days before the event.

1806-Sander-Watermarking

Event Venue & Nearby Stays

3 Rue Rossini, 3 Rue Rossini, Paris, France