Personalized differential privacy budgets based on re-identification risk in federated learning produce lower error rates than fixed budgets on medical tabular data.
Survey on federated learning threats: Concepts, taxonomy on attacks and defences, experimental study and challenges
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A decision-tree-based federated learning model with differential privacy is proposed and the resulting drop in explainability is measured via SHAP and MDI.
citing papers explorer
-
Privacy Preserving Machine Learning Workflow: from Anonymization to Personalized Differential Privacy Budgets in Federated Learning
Personalized differential privacy budgets based on re-identification risk in federated learning produce lower error rates than fixed budgets on medical tabular data.
-
Towards Explainable Federated Learning: Understanding the Impact of Differential Privacy
A decision-tree-based federated learning model with differential privacy is proposed and the resulting drop in explainability is measured via SHAP and MDI.