Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks

1 code implementation • 26 Jan 2023 • Louis Bethune, Paul Novello, Thibaut Boissin, Guillaume Coiffier, Mathieu Serrurier, Quentin Vincenot, Andres Troya-Galvis

The distance to the support can be interpreted as a normality score, and its approximation using 1-Lipschitz neural networks provides robustness bounds against $l2$ adversarial attacks, an under-explored weakness of deep learning-based OCC algorithms.

Image Generation One-Class Classification

Tackling Algorithmic Bias in Neural-Network Classifiers using Wasserstein-2 Regularization

no code implementations • 15 Aug 2019 • Laurent Risser, Alberto Gonzalez Sanz, Quentin Vincenot, Jean-Michel Loubes

We then introduce in this paper a new method to temper the algorithmic bias in Neural-Network based classifiers.