RobWE introduces a novel watermark embedding approach to safeguard ownership of personalized models in federated learning. The scheme decouples the embedding process into head layer and representation layer, ensuring client privacy and model aggregation compatibility. By employing watermark slice embedding and tamper detection mechanisms, RobWE achieves superior fidelity, reliability, and robustness compared to state-of-the-art schemes.
Naar een andere taal
vanuit de broninhoud
arxiv.org
Belangrijkste Inzichten Gedestilleerd Uit
by Yang Xu,Yunl... om arxiv.org 03-01-2024
https://arxiv.org/pdf/2402.19054.pdfDiepere vragen