Core Concepts
FedTracker provides ownership verification and traceability for FL models through watermarking and local fingerprints.
Abstract
FedTracker introduces a novel framework for protecting FL models by embedding a global watermark and unique local fingerprints. The global watermark mechanism authenticates ownership, while local fingerprints identify the model's origin. The framework addresses challenges of utility preservation during watermark embedding and differentiation between Client models. FedTracker leverages Continual Learning principles to embed watermarks effectively. Experimental results demonstrate its effectiveness in ownership verification, traceability, fidelity, and robustness against attacks.
Stats
Global memory is defined as the accumulated global gradients from the first iteration to the current iteration.
The Fingerprint Similarity Score (FSS) measures the similarity of extracted fingerprints with continuous outputs.
WAFFLE proposes a server-side FL watermarking method using backdoor-based watermarks.