Turning Federated Learning Systems Into Covert Channels

no code implementations • 21 Apr 2021 • Gabriele Costa, Fabio Pinelli, Simone Soderi, Gabriele Tolomei

Although the effect of the model poisoning is negligible to other participants, and does not alter the overall model performance, it can be observed by a malicious receiver and used to transmit a single bit.

Federated Learning Model Poisoning