Differentially Private Learning Needs Hidden State (Or Much Faster Convergence)

10 March 2022

Papers citing "Differentially Private Learning Needs Hidden State (Or Much Faster Convergence)"

32 / 32 papers shown

Title
Empirical Privacy Variance Yuzheng Hu Fan Wu Ruicheng Xian Yuhang Liu Lydia Zakynthinou Pritish Kamath Chiyuan Zhang David A. Forsyth 64 0 0 16 Mar 2025
Controlled privacy leakage propagation throughout overlapping grouped learning Shahrzad Kiani Franziska Boenisch S. Draper FedML 72 0 0 06 Mar 2025
An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses Hao Liang Feiyu Xiong Xinlei He Kaishun He Hong Xing 47 0 0 25 Feb 2025
Differential privacy guarantees of Markov chain Monte Carlo algorithms Andrea Bertazzi Tim Johnston Gareth O. Roberts Alain Durmus 38 0 0 24 Feb 2025
Guarding the Privacy of Label-Only Access to Neural Network Classifiers via iDP Verification Anan Kabaha Dana Drachsler-Cohen AAML 48 0 0 23 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-Preserving Split Learning with Vision Transformers using Patch-Wise Random and Noisy CutMix Yang Jin Sihun Baek Lei Zhang Hyelin Nam Praneeth Vepakomma Ramesh Raskar Mehdi Bennis Seong-Lyun Kim 36 2 0 02 Aug 2024
Differentially Private Neural Network Training under Hidden State Assumption Ding Chen Chen Liu FedML 32 0 0 11 Jul 2024
Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model Tudor Cebere A. Bellet Nicolas Papernot 30 9 0 23 May 2024
Nearly Tight Black-Box Auditing of Differentially Private Machine Learning Meenatchi Sundaram Muthu Selva Annamalai Emiliano De Cristofaro 44 11 0 23 May 2024
Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning Chendi Wang Yuqing Zhu Weijie J. Su Yu-Xiang Wang AAML 58 4 0 14 May 2024
Diffusion Denoising as a Certified Defense against Clean-label Poisoning Sanghyun Hong Nicholas Carlini Alexey Kurakin DiffM 53 3 0 18 Mar 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
Shifted Interpolation for Differential Privacy Jinho Bok Weijie Su Jason M. Altschuler 33 8 0 01 Mar 2024
Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning Eli Chien Haoyu Wang Ziang Chen Pan Li MU 37 8 0 18 Jan 2024
Privacy Amplification by Iteration for ADMM with (Strongly) Convex Objective Functions T.-H. Hubert Chan Hao Xie Mengshi Zhao 37 1 0 14 Dec 2023
Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach Xinwei Zhang Zhiqi Bu Zhiwei Steven Wu Mingyi Hong 16 7 0 24 Nov 2023
Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$ -Differential Privacy Chendi Wang Buxin Su Jiayuan Ye Reza Shokri Weijie J. Su FedML 21 10 0 30 Oct 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
Have it your way: Individualized Privacy Assignment for DP-SGD Franziska Boenisch Christopher Muhl Adam Dziedzic Roy Rinberg Nicolas Papernot 18 18 0 29 Mar 2023
Faster high-accuracy log-concave sampling via algorithmic warm starts Jason M. Altschuler Sinho Chewi 29 34 0 20 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
Resolving the Mixing Time of the Langevin Algorithm to its Stationary Distribution for Log-Concave Sampling Jason M. Altschuler Kunal Talwar 38 24 0 16 Oct 2022
TAN Without a Burn: Scaling Laws of DP-SGD Tom Sander Pierre Stock Alexandre Sablayrolles FedML 47 42 0 07 Oct 2022
Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss Jason M. Altschuler Kunal Talwar FedML 36 57 0 27 May 2022
Can Stochastic Gradient Langevin Dynamics Provide Differential Privacy for Deep Learning? Guy Heller Ethan Fetaya BDL 38 3 0 11 Oct 2021
Stochastic Training is Not Necessary for Generalization Jonas Geiping Micah Goldblum Phillip E. Pope Michael Moeller Tom Goldstein 89 72 0 29 Sep 2021
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 168 350 0 25 Sep 2021
Practical and Private (Deep) Learning without Sampling or Shuffling Peter Kairouz Brendan McMahan Shuang Song Om Thakkar Abhradeep Thakurta Zheng Xu FedML 182 194 0 26 Feb 2021
Extracting Training Data from Large Language Models Nicholas Carlini Florian Tramèr Eric Wallace Matthew Jagielski Ariel Herbert-Voss ... Tom B. Brown D. Song Ulfar Erlingsson Alina Oprea Colin Raffel MLAU SILM 290 1,824 0 14 Dec 2020