DP-MacAdam combines adaptive clipping and Adam-style momentum in DP-SGD by sharing bias-free empirical gradient statistics, achieving higher utility than DP-SGD, AdaClip, and DP-Adam without manual clipping threshold tuning.
T., Yu, F
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
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.
Deterministic gradient-norm bounds in variational QML control DP-SGD clipping bias, so quantum models retain more accuracy than matched classical models under the same privacy budget.
DPSR-CG corrects the privacy accounting for selective release in DPSGD by addressing sampling probability variation and reports strong empirical results on MNIST, CIFAR-10, IMDB, and FMNIST while claiming strict privacy.
CA-ADP adjusts differential privacy noise per mini-batch class composition to improve F-scores by 3.3-8.5% over standard DP on three fall-detection datasets while claiming formal (ε,δ) guarantees.
citing papers explorer
-
DP-MacAdam: Differentially Private Mechanism with Adaptive Clipping and Adaptive Momentum
DP-MacAdam combines adaptive clipping and Adam-style momentum in DP-SGD by sharing bias-free empirical gradient statistics, achieving higher utility than DP-SGD, AdaClip, and DP-Adam without manual clipping threshold tuning.
-
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.
-
Private training in quantum machine learning
Deterministic gradient-norm bounds in variational QML control DP-SGD clipping bias, so quantum models retain more accuracy than matched classical models under the same privacy budget.
-
Revisiting Privacy Amplification by Subsampling in Selective Release DPSGD
DPSR-CG corrects the privacy accounting for selective release in DPSGD by addressing sampling probability variation and reports strong empirical results on MNIST, CIFAR-10, IMDB, and FMNIST while claiming strict privacy.
-
Class-Aware Adaptive Differential Privacy in Deep Learning for Sensor-Based Fall Detection
CA-ADP adjusts differential privacy noise per mini-batch class composition to improve F-scores by 3.3-8.5% over standard DP on three fall-detection datasets while claiming formal (ε,δ) guarantees.