Turning Federated Learning Systems Into Covert Channels

arXiv:2104.10561v3 Announce Type: replace-cross
Abstract: Federated learning (FL) goes beyond traditional, centralized machine learning by distributing model training among a large collection of edge clients. These clients cooperatively train a global, e.g., cloud-hosted, model without disclosing their local, private training data. The global model is then shared among all the participants which use it for local predictions. In this paper, we put forward a novel attacker model aiming at turning FL systems into covert channels to implement a stealth communication …

abstract arxiv beyond channels cloud collection cs.cr cs.lg data edge federated learning global learning systems machine machine learning systems train training training data type