
The author presents RobWE as a solution to protect personalized model ownership in federated learning by decoupling watermark embedding and employing a detection mechanism to ensure robustness.


coremsg

RobWE-Robust-Watermark-Embedding-for-Personalized-Federated-Learning-Model-Ownership-Protection


RobWE: Robust Watermark Embedding for Personalized Federated Learning Model Ownership Protection


title_rewrite


RobWE provides a robust watermark embedding scheme to protect personalized models in federated learning, outperforming existing methods.
