Cover Image

To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Annamalai, Meenatchi Sundaram Muthu Selva, Balle, Borja, Hayes, Jamie, De Cristofaro, Emiliano
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
by: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Published: (2024)

The Elusive Pursuit of Reproducing PATE-GAN: Benchmarking, Auditing, Debugging
by: Ganev, Georgi, et al.
Published: (2024)

Understanding the Impact of Data Domain Extraction on Synthetic Data Privacy
by: Ganev, Georgi, et al.
Published: (2025)

The Importance of Being Discrete: Measuring the Impact of Discretization in End-to-End Differentially Private Synthetic Data
by: Ganev, Georgi, et al.
Published: (2025)

"What do you want from theory alone?" Experimenting with Tight Auditing of Differentially Private Synthetic Data Generation
by: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Published: (2024)

Tight Auditing of Differential Privacy in MST and AIM
by: Ganev, Georgi, et al.
Published: (2026)

CLIOPATRA: Extracting Private Information from LLM Insights
by: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Published: (2026)

A Unified Framework for Adversary-Aware Differential Privacy Bounds
by: Swanberg, Marika, et al.
Published: (2025)

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

A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Data
by: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Published: (2023)

Beyond the Crawl: Unmasking Browser Fingerprinting in Real User Interactions
by: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Published: (2025)

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)

Weights Shuffling for Improving DPSGD in Transformer-based Models
by: Yang, Jungang, et al.
Published: (2024)

Fooling SHAP with Output Shuffling Attacks
by: Yuan, Jun, 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)

Beyond Statistical Estimation: Differentially Private Individual Computation via Shuffling
by: Wang, Shaowei, et al.
Published: (2024)

Near-Optimal Reinforcement Learning with Shuffle Differential Privacy
by: Bai, Shaojie, et al.
Published: (2024)

Defense against Poisoning Attacks under Shuffle-DP
by: Wang, Siyi, et al.
Published: (2026)

Differentially Private Block-wise Gradient Shuffle for Deep Learning
by: Zagardo, David
Published: (2024)

How to Securely Shuffle? A survey about Secure Shufflers for privacy-preserving computations
by: Damie, Marc, et al.
Published: (2025)

Shuffling for Semantic Secrecy
by: Chen, Fupei, et al.
Published: (2025)

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

Analysis of Shuffling Beyond Pure Local Differential Privacy
by: Takagi, Shun, et al.
Published: (2026)

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

Learning from End User Data with Shuffled Differential Privacy over Kernel Densities
by: Wagner, Tal
Published: (2025)

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

Verifying the Fisher-Yates Shuffle Algorithm in Dafny
by: Zetzsche, Stefan, et al.
Published: (2025)

Mutual Information Bounds in the Shuffle Model
by: Su, Pengcheng, et al.
Published: (2025)

Bayesian Advantage of Re-Identification Attack in the Shuffle Model
by: Su, Pengcheng, et al.
Published: (2025)

A Complexity Hierarchy of Shuffles in Card-Based Protocols
by: Ono, Tomoki, et al.
Published: (2026)

Privacy Amplification via Shuffling: Unified, Simplified, and Tightened
by: Wang, Shaowei, et al.
Published: (2023)

Private Vector Mean Estimation in the Shuffle Model: Optimal Rates Require Many Messages
by: Asi, Hilal, et al.
Published: (2024)

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

Beyond the Calibration Point: Mechanism Comparison in Differential Privacy
by: Kaissis, Georgios, et al.
Published: (2024)

Graphical vs. Deep Generative Models: Measuring the Impact of Differentially Private Mechanisms and Budgets on Utility
by: Ganev, Georgi, et al.
Published: (2023)

On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference
by: Li, Zhengyi, et al.
Published: (2026)

Enhanced Privacy Bound for Shuffle Model with Personalized Privacy
by: Liu, Yixuan, et al.
Published: (2024)

The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasets
by: Ganev, Georgi, et al.
Published: (2023)