Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss

27 May 2022

Papers citing "Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss"

19 / 19 papers shown

Title
An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses Hao Liang W. Zhang Xinlei He Kaishun He Hong Xing 47 0 0 25 Feb 2025
Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios Sangyeon Yoon Wonje Jeung Albert No 85 0 0 02 Dec 2024
The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD Thomas Steinke Milad Nasr Arun Ganesh Borja Balle Christopher A. Choquette-Choo Matthew Jagielski Jamie Hayes Abhradeep Thakurta Adam Smith Andreas Terzis 34 7 0 08 Oct 2024
Privacy of the last iterate in cyclically-sampled DP-SGD on nonconvex composite losses Weiwei Kong Mónica Ribero 28 3 0 07 Jul 2024
Differentially Private Graph Diffusion with Applications in Personalized PageRanks Rongzhe Wei Eli Chien P. Li 42 5 0 22 Jun 2024
Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping Umut Simsekli Mert Gurbuzbalaban S. Yıldırım Lingjiong Zhu 38 2 0 04 Mar 2024
Tight Group-Level DP Guarantees for DP-SGD with Sampling via Mixture of Gaussians Mechanisms Arun Ganesh 24 2 0 17 Jan 2024
Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD Anvith Thudi Hengrui Jia Casey Meehan Ilia Shumailov Nicolas Papernot 30 3 0 01 Jul 2023
Privacy Loss of Noisy Stochastic Gradient Descent Might Converge Even for Non-Convex Losses S. Asoodeh Mario Díaz 20 6 0 17 May 2023
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
From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning Edwige Cyffers A. Bellet D. Basu FedML 29 5 0 24 Feb 2023
Tight Auditing of Differentially Private Machine Learning Milad Nasr Jamie Hayes Thomas Steinke Borja Balle Florian Tramèr Matthew Jagielski Nicholas Carlini Andreas Terzis FedML 35 52 0 15 Feb 2023
Bounding Training Data Reconstruction in DP-SGD Jamie Hayes Saeed Mahloujifar Borja Balle AAML FedML 33 39 0 14 Feb 2023
Privacy Risk for anisotropic Langevin dynamics using relative entropy bounds Anastasia Borovykh N. Kantas P. Parpas G. Pavliotis 19 1 0 01 Feb 2023
Reconstructing Training Data from Model Gradient, Provably Zihan Wang Jason D. Lee Qi Lei FedML 29 24 0 07 Dec 2022
Resolving the Mixing Time of the Langevin Algorithm to its Stationary Distribution for Log-Concave Sampling Jason M. Altschuler Kunal Talwar 35 24 0 16 Oct 2022
Differentially Private Learning Needs Hidden State (Or Much Faster Convergence) Jiayuan Ye Reza Shokri FedML 27 44 0 10 Mar 2022
Private Convex Optimization via Exponential Mechanism Sivakanth Gopi Y. Lee Daogao Liu 83 52 0 01 Mar 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 159 350 0 25 Sep 2021