Cover Image

Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cebere, Tudor, Bellet, Aurélien, Papernot, Nicolas
Format:	Preprint
Published:	2024
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

Private Rate-Constrained Optimization with Applications to Fair Learning
by: Yaghini, Mohammad, et al.
Published: (2025)

Privacy Auditing with Zero (0) Training Run
by: Cebere, Tudor, et al.
Published: (2026)

Privacy in Theory, Bugs in Practice: Grey-Box Auditing of Differential Privacy Libraries
by: Cebere, Tudor, et al.
Published: (2026)

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

DP-SGD Without Clipping: The Lipschitz Neural Network Way
by: Bethune, Louis, 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)

Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
by: Thudi, Anvith, 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)

Privacy Attacks in Decentralized Learning
by: Mrini, Abdellah El, et al.
Published: (2024)

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

Rényi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration
by: Pierquin, Clément, et al.
Published: (2023)

Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios
by: Yoon, Sangyeon, et al.
Published: (2024)

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

Privacy Amplification Through Synthetic Data: Insights from Linear Regression
by: Pierquin, Clément, et al.
Published: (2025)

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)

On the Privacy Risk of In-context Learning
by: Duan, Haonan, et al.
Published: (2024)

Differentially Private Decentralized Learning with Random Walks
by: Cyffers, Edwige, et al.
Published: (2024)

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

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

Privacy Amplification Persists under Unlimited Synthetic Data Release
by: Pierquin, Clément, et al.
Published: (2026)

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

Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy
by: Hayes, Jamie, 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)

Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging
by: Cyffers, Edwige, et al.
Published: (2022)

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

Augment then Smooth: Reconciling Differential Privacy with Certified Robustness
by: Wu, Jiapeng, et al.
Published: (2023)

Byzantine Failures Harm the Generalization of Robust Distributed Learning Algorithms More Than Data Poisoning
by: Boudou, Thomas, et al.
Published: (2025)

The Relative Gaussian Mechanism and its Application to Private Gradient Descent
by: Hendrikx, Hadrien, et al.
Published: (2023)

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

Visual Privacy Auditing with Diffusion Models
by: Schwethelm, Kristian, et al.
Published: (2024)

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)

Decentralised, Collaborative, and Privacy-preserving Machine Learning for Multi-Hospital Data
by: Fang, Congyu, et al.
Published: (2024)

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

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

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

Observational Auditing of Label Privacy
by: Kalemaj, Iden, et al.
Published: (2025)

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