로그인
통찰 - Watermark Embedding in Federated Learning
RobWE: Robust Watermark Embedding for Personalized Federated Learning Model Ownership Protection
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.
RobWE: Robust Watermark Embedding for Personalized Federated Learning Model Ownership Protection
RobWE provides a robust watermark embedding scheme to protect personalized models in federated learning, outperforming existing methods.
