Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model

23 May 2024

Papers citing "Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model"

42 / 42 papers shown

Title
Empirical Privacy Variance Yuzheng Hu Fan Wu Ruicheng Xian Yuhang Liu Lydia Zakynthinou Pritish Kamath Chiyuan Zhang David A. Forsyth 85 0 0 16 Mar 2025
Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios Sangyeon Yoon Wonje Jeung Albert No 121 0 0 02 Dec 2024
Data Deletion for Linear Regression with Noisy SGD Zhangjie Xia Chi-Hua Wang Guang Cheng 79 2 0 12 Oct 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 82 7 0 08 Oct 2024
It's Our Loss: No Privacy Amplification for Hidden State DP-SGD With Non-Convex Loss Meenatchi Sundaram Muthu Selva Annamalai 61 8 0 09 Jul 2024
Nearly Tight Black-Box Auditing of Differentially Private Machine Learning Meenatchi Sundaram Muthu Selva Annamalai Emiliano De Cristofaro 75 12 0 23 May 2024
Privacy Backdoors: Stealing Data with Corrupted Pretrained Models Shanglun Feng Florian Tramèr SILM 75 16 0 30 Mar 2024
Shifted Interpolation for Differential Privacy Jinho Bok Weijie Su Jason M. Altschuler 85 9 0 01 Mar 2024
Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$ -Differential Privacy Chendi Wang Buxin Su Jiayuan Ye Reza Shokri Weijie J. Su FedML 52 11 0 30 Oct 2023
Privacy Loss of Noisy Stochastic Gradient Descent Might Converge Even for Non-Convex Losses S. Asoodeh Mario Díaz 46 6 0 17 May 2023
Privacy Auditing with One (1) Training Run Thomas Steinke Milad Nasr Matthew Jagielski 88 79 0 15 May 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 51 50 0 15 Feb 2023
One-shot Empirical Privacy Estimation for Federated Learning Galen Andrew Peter Kairouz Sewoong Oh Alina Oprea H. B. McMahan Vinith Suriyakumar FedML 79 35 0 06 Feb 2023
A General Framework for Auditing Differentially Private Machine Learning Fred Lu Joseph Munoz Maya Fuchs Tyler LeBlond Elliott Zaresky-Williams Edward Raff Francis Ferraro Brian Testa FedML 34 36 0 16 Oct 2022
CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning Samuel Maddock Alexandre Sablayrolles Pierre Stock FedML 100 22 0 06 Oct 2022
Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributions Vadym Doroshenko Badih Ghazi Pritish Kamath Ravi Kumar Pasin Manurangsi 46 41 0 10 Jul 2022
Reconstructing Training Data from Trained Neural Networks Niv Haim Gal Vardi Gilad Yehudai Ohad Shamir Michal Irani 56 134 0 15 Jun 2022
Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss Jason M. Altschuler Kunal Talwar FedML 87 57 0 27 May 2022
Unlocking High-Accuracy Differentially Private Image Classification through Scale Soham De Leonard Berrada Jamie Hayes Samuel L. Smith Borja Balle 66 223 0 28 Apr 2022
Differentially Private Learning Needs Hidden State (Or Much Faster Convergence) Jiayuan Ye Reza Shokri FedML 66 44 0 10 Mar 2022
Reconstructing Training Data with Informed Adversaries Borja Balle Giovanni Cherubin Jamie Hayes MIACV AAML 77 162 0 13 Jan 2022
Membership Inference Attacks From First Principles Nicholas Carlini Steve Chien Milad Nasr Shuang Song Andreas Terzis Florian Tramèr MIACV MIALM 46 663 0 07 Dec 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 219 357 0 25 Sep 2021
Adaptive Machine Unlearning Varun Gupta Christopher Jung Seth Neel Aaron Roth Saeed Sharifi-Malvajerdi Chris Waites MU 53 177 0 08 Jun 2021
Numerical Composition of Differential Privacy Sivakanth Gopi Y. Lee Lukas Wutschitz 44 176 0 05 Jun 2021
Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning Haibo Yang Minghong Fang Jia Liu FedML 50 256 0 27 Jan 2021
Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning Milad Nasr Shuang Song Abhradeep Thakurta Nicolas Papernot Nicholas Carlini MIACV FedML 105 219 0 11 Jan 2021
Privacy Amplification by Decentralization Edwige Cyffers A. Bellet FedML 87 40 0 09 Dec 2020
Descent-to-Delete: Gradient-Based Methods for Machine Unlearning Seth Neel Aaron Roth Saeed Sharifi-Malvajerdi MU 45 264 0 06 Jul 2020
Auditing Differentially Private Machine Learning: How Private is Private SGD? Matthew Jagielski Jonathan R. Ullman Alina Oprea FedML 53 240 0 13 Jun 2020
Machine Unlearning Lucas Bourtoule Varun Chandrasekaran Christopher A. Choquette-Choo Hengrui Jia Adelin Travers Baiwu Zhang David Lie Nicolas Papernot MU 103 830 0 09 Dec 2019
PyTorch: An Imperative Style, High-Performance Deep Learning Library Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury ... Sasank Chilamkurthy Benoit Steiner Lu Fang Junjie Bai Soumith Chintala ODL 300 42,038 0 03 Dec 2019
Certified Data Removal from Machine Learning Models Chuan Guo Tom Goldstein Awni Y. Hannun Laurens van der Maaten MU 77 434 0 08 Nov 2019
Privacy Amplification by Mixing and Diffusion Mechanisms Borja Balle Gilles Barthe Marco Gaboardi J. Geumlek 26 41 0 29 May 2019
Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity Ulfar Erlingsson Vitaly Feldman Ilya Mironov A. Raghunathan Kunal Talwar Abhradeep Thakurta 170 423 0 29 Nov 2018
Privacy Amplification by Iteration Vitaly Feldman Ilya Mironov Kunal Talwar Abhradeep Thakurta FedML 50 171 0 20 Aug 2018
Membership Inference Attacks against Machine Learning Models Reza Shokri M. Stronati Congzheng Song Vitaly Shmatikov SLR MIALM MIACV 216 4,075 0 18 Oct 2016
Deep Learning with Differential Privacy Martín Abadi Andy Chu Ian Goodfellow H. B. McMahan Ilya Mironov Kunal Talwar Li Zhang FedML SyDa 170 6,069 0 01 Jul 2016
Deep Residual Learning for Image Recognition Kaiming He Xinming Zhang Shaoqing Ren Jian Sun MedIm 1.5K 192,638 0 10 Dec 2015
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification Kaiming He Xinming Zhang Shaoqing Ren Jian Sun VLM 215 18,534 0 06 Feb 2015
The Composition Theorem for Differential Privacy Peter Kairouz Sewoong Oh Pramod Viswanath 93 677 0 04 Nov 2013
What Can We Learn Privately? S. Kasiviswanathan Homin K. Lee Kobbi Nissim Sofya Raskhodnikova Adam D. Smith 99 1,459 0 06 Mar 2008