Fine-tuning BERT with the fixed-mini-batch FSRDP differential privacy accountant in a 4-client federated setup yields roughly 1-2% lower accuracy than RDP while using constant memory.
The secret sharer: Evaluating and testing unintended memorization in neural networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models
Fine-tuning BERT with the fixed-mini-batch FSRDP differential privacy accountant in a 4-client federated setup yields roughly 1-2% lower accuracy than RDP while using constant memory.