MLAI 2019, 05. Pablo Piantanida Learning Anonymized Representations with Mutual Information
Speaker: Pablo Piantanida, Associate Professor of Information Theory at CentraleSupelec Abstract: Statistical methods protecting sensitive information or the identity of the data owner have become critical to ensure privacy of individuals as well as of organizations. In this talk, we present a statistical anonymization method based on representation learning and deep neural networks. Our approach employs adversarial networks to perform a novel variational approximation of the mutual information between the
|
|