Watermarking in Secure Federated Learning: A Verification Framework Based on Client-Side Backdooring. (arXiv:2211.07138v2 [cs.CR] UPDATED)

Federated learning (FL) allows multiple participants to collaboratively build
deep learning (DL) models without directly sharing data. Consequently, the
issue of copyright protection in FL becomes important since unreliable
participants may gain access to the jointly trained model. Application of
homomorphic encryption (HE) in secure FL framework prevents the central server
from accessing plaintext models. Thus, it is no longer feasible to embed the
watermark at the central server using existing watermarking schemes. In this
paper, we propose a novel …

access application backdooring build client client-side copyright data deep learning encryption federated learning framework homomorphic encryption important issue may plaintext protection server sharing verification watermarking