1 code implementation • 24 Oct 2022 • Jean-Rémy Conti, Nathan Noiry, Vincent Despiegel, Stéphane Gentric, Stéphan Clémençon
In spite of the high performance and reliability of deep learning algorithms in a wide range of everyday applications, many investigations tend to show that a lot of models exhibit biases, discriminating against specific subgroups of the population (e. g. gender, ethnicity).
Ranked #1 on Face Verification on LFW
no code implementations • 5 May 2022 • Hervé Chabannne, Vincent Despiegel, Linda Guiga
We introduce a new wallet recovery process.
no code implementations • 29 Sep 2021 • Jean-Rémy Conti, Nathan Noiry, Stephan Clemencon, Vincent Despiegel, Stéphane Gentric
In spite of the high performance and reliability of deep learning algorithms in broad range everyday applications, many investigations tend to show that a lot of models exhibit biases, discriminating against some subgroups of the population.
no code implementations • 26 May 2020 • Hervé Chabanne, Vincent Despiegel, Linda Guiga
Given oracle access to a Neural Network (NN), it is possible to extract its underlying model.