4 citations · 6 across the 7 of their papers we have counts for
10 papers
Tight End-to-End Accounting for Differentially Private Synthetic Data
Georgi Ganev, Vadym Doroshenko, Arun Ganesh +3
Differentially private (DP) pipelines often combine heterogeneous mechanisms, yet their guarantees are best analyzed using different notions of privacy (e.g., bounded range, zCDP,…
Better Batches, Better Privacy: Random Allocation for DP-BandMF
Ryan McKenna, Arun Ganesh
The current state of the art for batch selection and noise addition in differentially private training is a combination of DP-BandMF (informally, DP-SGD where the noise added in tw…
JAX-Privacy: A library for differentially private machine learning
Ryan McKenna, Galen Andrew, Borja Balle +6
JAX-Privacy is a library designed to simplify the deployment of robust and performant mechanisms for differentially private machine learning. Guided by design principles of usabili…
Privacy Amplification for BandMF via -Min-Sep Subsampling
Andy Dong, Arun Ganesh
We study privacy amplification for BandMF, i.e., DP-SGD with correlated noise across iterations via a banded correlation matrix. We propose -min-sep subsampling, a new subsampli…
Tighter Privacy Analysis for Truncated Poisson Sampling
Arun Ganesh
We give a new privacy amplification analysis for truncated Poisson sampling, a Poisson sampling variant that truncates a batch if it exceeds a given maximum batch size.
Correlated Noise Mechanisms for Differentially Private Learning
Krishna Pillutla, Jalaj Upadhyay, Christopher A. Choquette-Choo +9
This monograph explores the design and analysis of correlated noise mechanisms for differential privacy (DP), focusing on their application to private training of AI and machine le…
It's My Data Too: Private ML for Datasets with Multi-User Training Examples
Arun Ganesh, Ryan McKenna, Brendan McMahan +2
We initiate a study of algorithms for model training with user-level differential privacy (DP), where each example may be attributed to multiple users, which we call the multi-attr…
Fine-Tuning Large Language Models with User-Level Differential Privacy
Zachary Charles, Arun Ganesh, Ryan McKenna +4
We investigate practical and scalable algorithms for training large language models (LLMs) with user-level differential privacy (DP) in order to provably safeguard all the examples…
Tight Group-Level DP Guarantees for DP-SGD with Sampling via Mixture of Gaussians Mechanisms
Arun Ganesh
We give a procedure for computing group-level -DP guarantees for DP-SGD, when using Poisson sampling or fixed batch size sampling. Up to discretization errors in the implem…
How Compression and Approximation Affect Efficiency in String Distance Measures
Arun Ganesh, Tomasz Kociumaka, Andrea Lincoln +1
Real-world data often comes in compressed form. Analyzing compressed data directly (without decompressing it) can save space and time by orders of magnitude. In this work, we focus…