LM-DP-SGD estimates layer-specific MIA risks from shadow models and reweights gradients to give stronger protection to vulnerable layers, improving the privacy-utility trade-off over uniform DP-SGD.
Function- consistent feature distillation.arXiv preprint arXiv:2304.11832
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
SFKD uses multi-level discrete wavelet transform plus dual-stream refinement and Gaussian-filtered frequency loss to transfer spatial and global information across heterogeneous models.
citing papers explorer
-
Mitigating Membership Inference in Intermediate Representations with Differentially Private Training
LM-DP-SGD estimates layer-specific MIA risks from shadow models and reweights gradients to give stronger protection to vulnerable layers, improving the privacy-utility trade-off over uniform DP-SGD.
-
SFKD: Spatial--Frequency Joint-Aware Heterogeneous Knowledge Distillation via Multi-Level Wavelet Spectral Interaction
SFKD uses multi-level discrete wavelet transform plus dual-stream refinement and Gaussian-filtered frequency loss to transfer spatial and global information across heterogeneous models.