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

International Workshop on Machine Learning for Signal Processing (MLSP), 2021

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"

18 / 18 papers shown

Title
Towards Reliable and Generalizable Differentially Private Machine Learning (Extended Version) Wenxuan Bao Vincent Bindschaedler AAML 144 0 0 21 Aug 2025
Forward Learning with Differential Privacy Mingqian Feng Zeliang Zhang Jinyang Jiang Yijie Peng Chenliang Xu 205 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 237 0 0 16 Dec 2024
R+R:Understanding Hyperparameter Effects in DP-SGDAsia-Pacific Computer Systems Architecture Conference (ACSA), 2024 Felix Morsbach J. Reubold T. Strufe 187 1 0 04 Nov 2024
Masked Differential Privacy David Schneider Sina Sajadmanesh Vikash Sehwag Saquib Sarfraz Rainer Stiefelhagen Lingjuan Lyu Vivek Sharma 190 1 0 22 Oct 2024
Nearly Tight Black-Box Auditing of Differentially Private Machine LearningNeural Information Processing Systems (NeurIPS), 2024 Meenatchi Sundaram Muthu Selva Annamalai Emiliano De Cristofaro 226 18 0 23 May 2024
Sparsity-Preserving Differentially Private Training of Large Embedding ModelsNeural Information Processing Systems (NeurIPS), 2023 Badih Ghazi Yangsibo Huang Pritish Kamath Ravi Kumar Pasin Manurangsi Amer Sinha Chiyuan Zhang 165 5 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 152 18 0 21 Aug 2023
Differentially Private Video Activity RecognitionIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2023 Zelun Luo Yuliang Zou Yijin Yang Zane Durante De-An Huang Zhiding Yu Chaowei Xiao L. Fei-Fei Anima Anandkumar PICV 180 5 0 27 Jun 2023
Differentially Private Image Classification by Learning Priors from Random ProcessesNeural Information Processing Systems (NeurIPS), 2023 Xinyu Tang Ashwinee Panda Vikash Sehwag Prateek Mittal 185 28 0 08 Jun 2023
Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser Models Florian A. Hölzl Daniel Rueckert Georgios Kaissis 237 4 0 30 Jan 2023
Differentially Private Image Classification from Features Harsh Mehta Walid Krichene Abhradeep Thakurta Alexey Kurakin Ashok Cutkosky 213 10 0 24 Nov 2022
Differentially Private Diffusion Models Tim Dockhorn Tianshi Cao Arash Vahdat Karsten Kreis DiffM 274 120 0 18 Oct 2022
Kernel Normalized Convolutional Networks for Privacy-Preserving Machine Learning Reza Nasirigerdeh Javad Torkzadehmahani Daniel Rueckert Georgios Kaissis 172 1 0 30 Sep 2022
SmoothNets: Optimizing CNN architecture design for differentially private deep learning Nicolas W. Remerscheid Alexander Ziller Daniel Rueckert Georgios Kaissis 103 7 0 09 May 2022
Large Scale Transfer Learning for Differentially Private Image Classification Harsh Mehta Abhradeep Thakurta Alexey Kurakin Ashok Cutkosky 172 48 0 06 May 2022
Unlocking High-Accuracy Differentially Private Image Classification through Scale Soham De Leonard Berrada Jamie Hayes Samuel L. Smith Borja Balle 255 258 0 28 Apr 2022
Differentially private training of residual networks with scale normalisation Helena Klause Alexander Ziller Daniel Rueckert Kerstin Hammernik Georgios Kaissis 227 37 0 01 Mar 2022