DSFL claims a lightweight dual-server federated learning protocol that hides updates with additive noise and filters Byzantine clients using group deviation scores.
The challenges of data quality and data quality assessment in the big data era,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
DSFL: A Dual-Server Byzantine-Resilient Federated Learning Framework via Group-Based Secure Aggregation
DSFL claims a lightweight dual-server federated learning protocol that hides updates with additive noise and filters Byzantine clients using group deviation scores.