Paper Title
Towards Privacy Preservingand Efficiency in Fog Selection for Federated Learning
Abstract
Federated learning (FL) is an emerging trend related to the concept of distributed Machine Learning (ML).It
focuses on a collaborative training process, which is conducted locally on the dataset of the client devices in order to
preserve the users’ privacy. Nonetheless, this solution still suffers from many challenges dealing with the privacy, security,
and performance. In this research, we aim to enhance privacy, security and performance in federated learning by introducing
a novel policy-based FL approach. Our proposed solution ensures reliability, communications security, and heterogeneous
privacy (i.e., the users have different privacy attitudes and expectations.). In addition, it guarantees the performance in terms
of the dataset quality and scalability. To prove the effectiveness of our model, we perform a security and performance
evaluation by assuming a threat model with attackers having different behaviors. The evaluation analysis shows that our
proposed model provides a high level of security, a good performance, and a promising solution for the federated learning
environments.
Keywords - Federated Learning, Collaborative training, Heterogeneous privacy, Policy-based Approach.
Author - Noura Alhwidi, Noura Alqahtani, Latifah Almaiman, Molkarekik
Published : Volume-10,Issue-2 ( Feb, 2023 )
DOIONLINE Number - IJAECS-IRAJ-DOIONLINE-19816
View Here
|
|
| |
|
PDF |
| |
Viewed - 9 |
| |
Published on 2023-09-23 |
|