ContinuousBench shows non-private synthetic text transfers corpus-specific capabilities while state-of-the-art DP methods fail to do so even at ε=100.
hub
Smith, and Borja Balle
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
Differential privacy versions of TTA methods achieve privacy on ImageNet-C with small accuracy cost and can improve stability via clipping in continual settings.
Balanced Iteration Subsampling achieves stronger privacy amplification than Poisson subsampling in DP-SGD by eliminating participation variance while keeping uniform marginal participation.
PACZero achieves zero mutual information privacy in LLM fine-tuning via sign-quantized subset-aggregated ZO gradients, delivering near non-private accuracy on SST-2 at I=0.
FiBeR adds a closed-form filter-aware correction A(ω)σ_w² to the second-moment term for temporally filtered DP gradients, improving adaptive optimization performance.
DPrivBench is a new benchmark for evaluating LLMs on differential privacy reasoning, with results showing good performance on textbook mechanisms but substantial failures on advanced algorithms.
DPQuant uses epoch-wise probabilistic layer rotation and DP loss sensitivity to quantize only a changing subset of layers, reducing accuracy degradation from quantization noise in DP-SGD and delivering up to 2.21x throughput gains with under 2% accuracy drop.
DP-GD achieves minimax optimal non-asymptotic risk O(γ + γ²/ρ²) for well-conditioned high-dimensional data and power-law scaling for ill-conditioned power-law spectra, with the exponent depending on the privacy parameter ρ.
Identifies output label space as a privacy side-channel in DP continual learning, formalizes DP for CL, and demonstrates two mitigation methods yielding higher accuracy than prior work.
CAPS provides an iterative differentially private synthesis method that outperforms one-shot baselines on authentic educational real-world data.
Shuffled DP-SGD requires σ ≥ 1/√(2 ln M) or κ ≥ (1/√8)(1 - 1/√(4π ln M)) to limit adversarial advantage, preventing strong privacy and high utility simultaneously.
Add/remove adjacency in DP overstates attribute privacy relative to substitute adjacency; new auditing attacks confirm inconsistency with add/remove reports but consistency with substitute accounting.
DP-GRAPE reduces memory in differentially private neural network training by using random Gaussian projections on gradients instead of SVD, achieving comparable privacy-utility tradeoffs to DP-SGD and scaling to 6.7B parameter models.
Empirical study of DP transfer learning reveals that larger clipping bounds outperform under tight privacy and cumulative DP noise explains batch-size effects better than existing heuristics.
citing papers explorer
-
ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?
ContinuousBench shows non-private synthetic text transfers corpus-specific capabilities while state-of-the-art DP methods fail to do so even at ε=100.
-
Private and Stable Test-Time Adaptation with Differential Privacy
Differential privacy versions of TTA methods achieve privacy on ImageNet-C with small accuracy cost and can improve stability via clipping in continual settings.
-
Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD?
Balanced Iteration Subsampling achieves stronger privacy amplification than Poisson subsampling in DP-SGD by eliminating participation variance while keeping uniform marginal participation.
-
PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization
PACZero achieves zero mutual information privacy in LLM fine-tuning via sign-quantized subset-aggregated ZO gradients, delivering near non-private accuracy on SST-2 at I=0.
-
FIBER: A Differentially Private Optimizer with Filter-Aware Innovation Bias Correction
FiBeR adds a closed-form filter-aware correction A(ω)σ_w² to the second-moment term for temporally filtered DP gradients, improving adaptive optimization performance.
-
DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
DPrivBench is a new benchmark for evaluating LLMs on differential privacy reasoning, with results showing good performance on textbook mechanisms but substantial failures on advanced algorithms.
-
DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling
DPQuant uses epoch-wise probabilistic layer rotation and DP loss sensitivity to quantize only a changing subset of layers, reducing accuracy degradation from quantization noise in DP-SGD and delivering up to 2.21x throughput gains with under 2% accuracy drop.
-
High-Dimensional Private Linear Regression with Optimal Rates
DP-GD achieves minimax optimal non-asymptotic risk O(γ + γ²/ρ²) for well-conditioned high-dimensional data and power-law scaling for ill-conditioned power-law spectra, with the exponent depending on the privacy parameter ρ.
-
Privacy Leakage via Output Label Space and Differentially Private Continual Learning
Identifies output label space as a privacy side-channel in DP continual learning, formalizes DP for CL, and demonstrates two mitigation methods yielding higher accuracy than prior work.
-
Cyclic Adaptive Private Synthesis for Sharing Real-World Data in Education
CAPS provides an iterative differentially private synthesis method that outperforms one-shot baselines on authentic educational real-world data.
-
Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD
Shuffled DP-SGD requires σ ≥ 1/√(2 ln M) or κ ≥ (1/√8)(1 - 1/√(4π ln M)) to limit adversarial advantage, preventing strong privacy and high utility simultaneously.
-
Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
Add/remove adjacency in DP overstates attribute privacy relative to substitute adjacency; new auditing attacks confirm inconsistency with add/remove reports but consistency with substitute accounting.
-
Memory-Efficient Differentially Private Training with Gradient Random Projection
DP-GRAPE reduces memory in differentially private neural network training by using random Gaussian projections on gradients instead of SVD, achieving comparable privacy-utility tradeoffs to DP-SGD and scaling to 6.7B parameter models.
-
On Optimal Hyperparameters for Differentially Private Deep Transfer Learning
Empirical study of DP transfer learning reveals that larger clipping bounds outperform under tight privacy and cumulative DP noise explains batch-size effects better than existing heuristics.