Not all noise is accounted equally: How differentially private learning
benefits from large sampling rates

Not all noise is accounted equally: How differentially private learning benefits from large sampling rates

12 October 2021

Friedrich Dörmann

Christian Fischer Pedersen

ArXiv (abs)PDF HTML

Papers citing "Not all noise is accounted equally: How differentially private learning benefits from large sampling rates"

17 / 17 papers shown

Title
Forward Learning with Differential Privacy Mingqian Feng Zeliang Zhang Jinyang Jiang Yijie Peng Chenliang Xu 96 0 0 01 Apr 2025
The Impact of Generalization Techniques on the Interplay Among Privacy, Utility, and Fairness in Image Classification Ahmad Hassanpour Amir Zarei Khawla Mallat Anderson Santana de Oliveira Bian Yang 114 0 0 16 Dec 2024
R+R:Understanding Hyperparameter Effects in DP-SGD Felix Morsbach J. Reubold T. Strufe 77 0 0 04 Nov 2024
Masked Differential Privacy David Schneider Sina Sajadmanesh Vikash Sehwag Saquib Sarfraz Rainer Stiefelhagen Lingjuan Lyu Vivek Sharma 61 0 0 22 Oct 2024
Nearly Tight Black-Box Auditing of Differentially Private Machine Learning Meenatchi Sundaram Muthu Selva Annamalai Emiliano De Cristofaro 98 14 0 23 May 2024
Sparsity-Preserving Differentially Private Training of Large Embedding Models Badih Ghazi Yangsibo Huang Pritish Kamath Ravi Kumar Pasin Manurangsi Amer Sinha Chiyuan Zhang 61 2 0 14 Nov 2023
Unlocking Accuracy and Fairness in Differentially Private Image Classification Leonard Berrada Soham De J. Shen Jamie Hayes Robert Stanforth David Stutz Pushmeet Kohli Samuel L. Smith Borja Balle 67 15 0 21 Aug 2023
Differentially Private Video Activity Recognition Zelun Luo Yuliang Zou Yijin Yang Zane Durante De-An Huang Zhiding Yu Chaowei Xiao L. Fei-Fei Anima Anandkumar PICV 85 5 0 27 Jun 2023
Differentially Private Image Classification by Learning Priors from Random Processes Xinyu Tang Ashwinee Panda Vikash Sehwag Prateek Mittal 89 21 0 08 Jun 2023
Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser Models Florian A. Hölzl Daniel Rueckert Georgios Kaissis 88 4 0 30 Jan 2023
Differentially Private Image Classification from Features Harsh Mehta Walid Krichene Abhradeep Thakurta Alexey Kurakin Ashok Cutkosky 113 8 0 24 Nov 2022
Differentially Private Diffusion Models Tim Dockhorn Tianshi Cao Arash Vahdat Karsten Kreis DiffM 89 100 0 18 Oct 2022
Kernel Normalized Convolutional Networks for Privacy-Preserving Machine Learning Reza Nasirigerdeh Javad Torkzadehmahani Daniel Rueckert Georgios Kaissis 40 1 0 30 Sep 2022
SmoothNets: Optimizing CNN architecture design for differentially private deep learning Nicolas W. Remerscheid Alexander Ziller Daniel Rueckert Georgios Kaissis 38 6 0 09 May 2022
Large Scale Transfer Learning for Differentially Private Image Classification Harsh Mehta Abhradeep Thakurta Alexey Kurakin Ashok Cutkosky 85 41 0 06 May 2022
Unlocking High-Accuracy Differentially Private Image Classification through Scale Soham De Leonard Berrada Jamie Hayes Samuel L. Smith Borja Balle 97 233 0 28 Apr 2022
Differentially private training of residual networks with scale normalisation Helena Klause Alexander Ziller Daniel Rueckert Kerstin Hammernik Georgios Kaissis 67 34 0 01 Mar 2022