A multi-round combination of Quality Inference and group-testing FedGT detects misbehaving clients and evaluates client contributions under secure aggregation, outperforming the original schemes on cross-silo benchmarks.
Machine learning with adversaries: Byzantine tolerant gradient descent,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Detect \& Score: Privacy-Preserving Misbehaviour Detection and Contribution Evaluation in Federated Learning
A multi-round combination of Quality Inference and group-testing FedGT detects misbehaving clients and evaluates client contributions under secure aggregation, outperforming the original schemes on cross-silo benchmarks.