certified-unlearning-neural-networks-icml-2025

Desaprendizaje certificado para redes neuronales Este repositorio contiene la implementación del artículo "Certified Unlearning for Neural Networks" ICML 2025. Métodos PABI Amplificación de privacidad por iteración : Gradient Clipping en el artículo DP-SGD : Con privacidad de grupo como se descri...

Certified Unlearning for Neural Networks

We address the problem of machine unlearning, where the goal is to remove the influence of specific training data from a model upon request, motivated by privacy concerns and regulatory requirements such as the "right to be forgotten." Unfortunately, existing methods rely on restrictive assumptio...