When Federated Learning meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protection
This addresses ownership protection for stakeholders using FL in sensitive domains like healthcare, but it is an incremental contribution as it reviews existing methods rather than introducing new ones.
The paper tackles the problem of protecting intellectual property in Federated Learning (FL) models, which are vulnerable to theft despite privacy-preserving features, by providing an overview of watermarking techniques designed for FL's unique constraints.
Federated Learning (FL) is a technique that allows multiple participants to collaboratively train a Deep Neural Network (DNN) without the need of centralizing 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.