Copertina

Tight Group-Level DP Guarantees for DP-SGD with Sampling via Mixture of Gaussians Mechanisms

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Ganesh, Arun
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Cryptography and Security Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD
di: Ertan, Murat Bilgehan, et al.
Pubblicazione: (2026)

DP-SGD with weight clipping
di: Barczewski, Antoine, et al.
Pubblicazione: (2023)

Balls-and-Bins Sampling for DP-SGD
di: Chua, Lynn, et al.
Pubblicazione: (2024)

FlashDP: Private Training Large Language Models with Efficient DP-SGD
di: Wang, Liangyu, et al.
Pubblicazione: (2025)

To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling
di: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Pubblicazione: (2024)

Trade-off Functions for DP-SGD with Subsampling based on Random Shuffling: Tight Upper and Lower Bounds
di: van Dijk, Marten, et al.
Pubblicazione: (2026)

R+R:Understanding Hyperparameter Effects in DP-SGD
di: Morsbach, Felix, et al.
Pubblicazione: (2024)

On the Convergence of DP-SGD with Adaptive Clipping
di: Shulgin, Egor, et al.
Pubblicazione: (2024)

DP-SGD Without Clipping: The Lipschitz Neural Network Way
di: Bethune, Louis, et al.
Pubblicazione: (2023)

How Private are DP-SGD Implementations?
di: Chua, Lynn, et al.
Pubblicazione: (2024)

Optimal Rates for $O(1)$-Smooth DP-SCO with a Single Epoch and Large Batches
di: Choquette-Choo, Christopher A., et al.
Pubblicazione: (2024)

Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
di: Cebere, Tudor, et al.
Pubblicazione: (2024)

Closed-Form Bounds for DP-SGD against Record-level Inference
di: Cherubin, Giovanni, et al.
Pubblicazione: (2024)

Lap2: Revisiting Laplace DP-SGD for High Dimensions via Majorization Theory
di: Mohammady, Meisam, et al.
Pubblicazione: (2026)

Gaussian DP for Reporting Differential Privacy Guarantees in Machine Learning
di: Gomez, Juan Felipe, et al.
Pubblicazione: (2025)

The Hitchhiker's Guide to Efficient, End-to-End, and Tight DP Auditing
di: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Pubblicazione: (2025)

Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD?
di: Dong, Andy, et al.
Pubblicazione: (2026)

Have it your way: Individualized Privacy Assignment for DP-SGD
di: Boenisch, Franziska, et al.
Pubblicazione: (2023)

Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
di: Thudi, Anvith, et al.
Pubblicazione: (2023)

It's Our Loss: No Privacy Amplification for Hidden State DP-SGD With Non-Convex Loss
di: Annamalai, Meenatchi Sundaram Muthu Selva
Pubblicazione: (2024)

Scalable DP-SGD: Shuffling vs. Poisson Subsampling
di: Chua, Lynn, et al.
Pubblicazione: (2024)

Linear-Time User-Level DP-SCO via Robust Statistics
di: Ghazi, Badih, et al.
Pubblicazione: (2025)

DP-KAN: Differentially Private Kolmogorov-Arnold Networks
di: Kalinin, Nikita P., et al.
Pubblicazione: (2024)

DP-LDMs: Differentially Private Latent Diffusion Models
di: Liu, Michael F., et al.
Pubblicazione: (2023)

DP-TLDM: Differentially Private Tabular Latent Diffusion Model
di: Zhu, Chaoyi, et al.
Pubblicazione: (2024)

SMOTE-DP: Improving Privacy-Utility Tradeoff with Synthetic Data
di: Zhou, Yan, et al.
Pubblicazione: (2025)

SMA-DP: Spectral Memory-Aware Differential Privacy for Deep Learning
di: Partohaghighi, Mohammad, et al.
Pubblicazione: (2026)

DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Sampling
di: Wei, Jianxin, et al.
Pubblicazione: (2022)

FairDP: Certified Fairness with Differential Privacy
di: Tran, Khang, et al.
Pubblicazione: (2023)

DP-Dueling: Learning from Preference Feedback without Compromising User Privacy
di: Saha, Aadirupa, et al.
Pubblicazione: (2024)

Training Set Reconstruction from Differentially Private Forests: How Effective is DP?
di: Gorgé, Alice, et al.
Pubblicazione: (2025)

DP-SGD-Global-Adapt-V2-S: Triad Improvements of Privacy, Accuracy and Fairness via Step Decay Noise Multiplier and Step Decay Upper Clipping Threshold
di: Chilukoti, Sai Venkatesh, et al.
Pubblicazione: (2023)

DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models
di: Sha, Haichao, et al.
Pubblicazione: (2026)

LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models
di: Yang, Qin, et al.
Pubblicazione: (2024)

Q-ShiftDP: A Differentially Private Parameter-Shift Rule for Quantum Machine Learning
di: Ngo, Hoang M., et al.
Pubblicazione: (2026)

DP-SPRT: Differentially Private Sequential Probability Ratio Tests
di: Michel, Thomas, et al.
Pubblicazione: (2025)

Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping
di: Şimşekli, Umut, et al.
Pubblicazione: (2024)

Auditable Early Stopping for Agentic Routing: Ledger-Verified Run-Wise Certificates under Local DP
di: Akhauri, Shivam
Pubblicazione: (2025)

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
di: Steinke, Thomas, et al.
Pubblicazione: (2024)

DP-TabICL: In-Context Learning with Differentially Private Tabular Data
di: Carey, Alycia N., et al.
Pubblicazione: (2024)