Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms under Composition

Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms under Composition

27 May 2024

Papers citing "Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms under Composition"

9 / 9 papers shown

Title
Balls-and-Bins Sampling for DP-SGD Lynn Chua Badih Ghazi Charlie Harrison Ethan Leeman Pritish Kamath Ravi Kumar Pasin Manurangsi Amer Sinha Chiyuan Zhang 80 3 0 21 Dec 2024
Scalable DP-SGD: Shuffling vs. Poisson Subsampling Lynn Chua Badih Ghazi Pritish Kamath Ravi Kumar Pasin Manurangsi Amer Sinha Chiyuan Zhang 30 5 0 06 Nov 2024
Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement Jeremiah Birrell Reza Ebrahimi R. Behnia Jason L. Pacheco 23 0 0 19 Aug 2024
How Private are DP-SGD Implementations? Lynn Chua Badih Ghazi Pritish Kamath Ravi Kumar Pasin Manurangsi Amer Sinha Chiyuan Zhang 28 12 0 26 Mar 2024
Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic Optimisation Ossi Raisa Joonas Jälkö Antti Honkela 22 6 0 06 Feb 2024
Private Fine-tuning of Large Language Models with Zeroth-order Optimization Xinyu Tang Ashwinee Panda Milad Nasr Saeed Mahloujifar Prateek Mittal 44 18 0 09 Jan 2024
How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy Natalia Ponomareva Hussein Hazimeh Alexey Kurakin Zheng Xu Carson E. Denison H. B. McMahan Sergei Vassilvitskii Steve Chien Abhradeep Thakurta 94 167 0 01 Mar 2023
Composition of Differential Privacy & Privacy Amplification by Subsampling Thomas Steinke 54 50 0 02 Oct 2022
Opacus: User-Friendly Differential Privacy Library in PyTorch Ashkan Yousefpour I. Shilov Alexandre Sablayrolles Davide Testuggine Karthik Prasad ... Sayan Gosh Akash Bharadwaj Jessica Zhao Graham Cormode Ilya Mironov VLM 144 348 0 25 Sep 2021