Cover Image

Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ertan, Murat Bilgehan, van Dijk, Marten
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization
by: Ertan, Murat Bilgehan, et al.
Published: (2026)

On the Evidentiary Limits of Membership Inference for Copyright Auditing
by: Ertan, Murat Bilgehan, et al.
Published: (2026)

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

Tight Group-Level DP Guarantees for DP-SGD with Sampling via Mixture of Gaussians Mechanisms
by: Ganesh, Arun
Published: (2024)

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

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

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

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

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

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

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

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

An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses
by: Liang, Hao, et al.
Published: (2025)

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

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

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

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

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

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

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

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

TOSSS: a CVE-based Software Security Benchmark for Large Language Models
by: Damie, Marc, et al.
Published: (2026)

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

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

Privacy Enhanced PEFT: Tensor Train Decomposition Improves Privacy Utility Tradeoffs under DP-SGD
by: Kunwar, Pradip, et al.
Published: (2026)

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

Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness
by: Chien, Eli, et al.
Published: (2024)

Efficient Unlearning with Privacy Guarantees
by: Domingo-Ferrer, Josep, et al.
Published: (2025)

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

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

SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy
by: Nahid, Md Mahadi Hasan, et al.
Published: (2024)

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

Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off
by: Li, Yuecheng, et al.
Published: (2024)

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

Auditing Differential Privacy Guarantees Using Density Estimation
by: Koskela, Antti, et al.
Published: (2024)

A New Analysis of Differential Privacy's Generalization Guarantees
by: Jung, Christopher, et al.
Published: (2019)

Synthetic Data: Revisiting the Privacy-Utility Trade-off
by: Sarmin, Fatima Jahan, et al.
Published: (2024)

The Fundamental Limits of Least-Privilege Learning
by: Stadler, Theresa, et al.
Published: (2024)

Differentially Private Relational Learning with Entity-level Privacy Guarantees
by: Huang, Yinan, et al.
Published: (2025)