Privacy Auditing of Lithium-Ion Battery Ageing Model by Recovering Time-Series Data Using Gradient Inversion Attack in Federated Learning

Privacy Auditing of Lithium-Ion Battery Ageing Model by Recovering Time-Series Data Using Gradient Inversion Attack in Federated Learning

The exchange of gradients is a widely used method in modelling systems for machine learning (e.g., distributed training, federated learning) in privacy-sensitive domains. Unfortunately, there are still privacy risks in federated learning, as servers can reconstruct clients‘ training data through gra...

Full description

Saved in:
Bibliographic Details
Main Authors: Kaspars Sudars, Ivars Namatevs, Arturs Nikulins, Kaspars Ozols
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied Sciences
Subjects:
federated learning
differential privacy
privacy auditing
gradient-based inversion attack
battery ageing modelling
Online Access:https://www.mdpi.com/2076-3417/15/10/5704
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://www.mdpi.com/2076-3417/15/10/5704

Similar Items