Securing Intellectual Property in Federated Learning
Résumé
Federated Learning (FL) is a technique that allows multiple participants to collaboratively train a Deep Neural Network (DNN) without the need to centralize their data and therefore comes with privacy-preserving properties making it attractive for application in sensitive contexts. However, it requires sharing participant models during the training process which makes them vulnerable to theft or unauthorized distribution by malicious actors. To address the issue of ownership rights protection in the context of Machine Learning (ML), DNN Watermarking methods have been developed during the last five years. Most existing works have focused on watermarking in a centralized manner, but only a few methods have been designed for FL and its unique constraints. In this paper, we provide an overview of recent advancements in Federated Learning watermarking, shedding light on the new challenges and opportunities that arise in this field.
Origine : Fichiers produits par l'(les) auteur(s)