DP-SelFT improves the privacy-utility trade-off for LLM fine-tuning by selecting robust layer subsets via DP synthetic data and perturbation-matched evaluation.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
A pivot-model abstraction method enables automatic migration of neural network implementations between frameworks such as PyTorch and TensorFlow while preserving functional equivalence.
citing papers explorer
-
DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models
DP-SelFT improves the privacy-utility trade-off for LLM fine-tuning by selecting robust layer subsets via DP synthetic data and perturbation-matched evaluation.
-
Towards Migrating Neural Network Implementations
A pivot-model abstraction method enables automatic migration of neural network implementations between frameworks such as PyTorch and TensorFlow while preserving functional equivalence.
- Geometry-Aware Localized Watermarking for Copyright Protection in Embedding-as-a-Service