Covert Channel Attack to Federated Learning Systems. (arXiv:2104.10561v2 [cs.CR] UPDATED)

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 infrastructure. The main
intuition is …

attack beyond channel clients cloud collection covert covert channel data edge federated federated learning global goes large local machine machine learning model training private systems train training training data