When Federated Learning Meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protection
Machine Learning and Knowledge Extraction · 2023-10-04 · 5 (4) · 1382-1406
DOI: 10.3390/make5040070 ↗At a glance
Journal article in Machine Learning and Knowledge Extraction, published online on 2023-10-04. Written by Mohammed Lansari and 5 co-authors. Cited 29 times so far (Crossref); 124 references. The full text is freely available (open access, CC BY 4.0). Funded by: European Union, CYBAILE industrial chair.
Abstract (original language)
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.
Funding
- European Union
- CYBAILE industrial chair
Cite
APA
Lansari, M., Bellafqira, R., Kapusta, K., Thouvenot, V., Bettan, O., & Coatrieux, G. (2023). When Federated Learning Meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protection. Machine Learning and Knowledge Extraction, 5(4), 1382-1406. https://doi.org/10.3390/make5040070
Vancouver
Lansari M, Bellafqira R, Kapusta K, Thouvenot V, Bettan O, Coatrieux G. When Federated Learning Meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protection. Machine Learning and Knowledge Extraction. 2023;5(4):1382-1406. doi:10.3390/make5040070
BibTeX
@article{Lansari2023,
author = {Lansari, Mohammed and Bellafqira, Reda and Kapusta, Katarzyna and Thouvenot, Vincent and Bettan, Olivier and Coatrieux, Gouenou},
title = {When Federated Learning Meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protection},
journal = {Machine Learning and Knowledge Extraction},
year = {2023},
volume = {5},
number = {4},
pages = {1382--1406},
doi = {10.3390/make5040070}
}
EUVIMED