The paper derives a per-client mutual-information bound for topology-aware leakage in differentially private federated learning and a min-max noise allocation that improves the bound over uniform noise when leverage scores are unequal.
Membership inference attacks against machine learning models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Topology-Aware Differential Privacy in Federated Learning
The paper derives a per-client mutual-information bound for topology-aware leakage in differentially private federated learning and a min-max noise allocation that improves the bound over uniform noise when leverage scores are unequal.