Article Dans Une Revue (Article De Synthèse) Machine Learning and Knowledge Extraction Année : 2023

When Federated Learning Meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protection

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. Among other advantages, it comes with privacy-preserving properties, making it attractive for application in sensitive contexts, such as health care or the military. Although the data are not explicitly exchanged, the training procedure requires sharing information about participants’ models. This makes the individual models 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.

Fichier principal
Vignette du fichier
make-05-00070-v2.pdf (1.32 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-04592168 , version 1 (29-05-2024)

Licence

Identifiants

Citer

Mohammed Lansari, Reda Bellafqira, Katarzyna Kapusta, Vincent Thouvenot, Olivier Bettan, et al.. When Federated Learning Meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protection. Machine Learning and Knowledge Extraction, 2023, 5, pp.1382-1406. ⟨10.3390/make5040070⟩. ⟨hal-04592168⟩
140 Consultations
362 Téléchargements

Altmetric

Partager

  • More