Turning Federated Learning Systems Into Covert Channels

Turning Federated Learning Systems Into Covert Channels

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...

Full description

Bibliographic Details
Main Authors: Gabriele Costa, Fabio Pinelli, Simone Soderi, Gabriele Tolomei
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Federated learning
adversarial attacks
machine learning security
covert channel
Online Access:https://ieeexplore.ieee.org/document/9984638/

Internet

https://ieeexplore.ieee.org/document/9984638/

Similar Items