Personalized differential privacy budgets based on re-identification risk in federated learning produce lower error rates than fixed budgets on medical tabular data.
A review of machine learning and deep learning applications
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.