Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams

16 February 2022

Papers citing "Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams"

46 / 46 papers shown

Title
An Inversion Theorem for Buffered Linear Toeplitz (BLT) Matrices and Applications to Streaming Differential Privacy H. B. McMahan Krishna Pillutla 31 0 0 30 Apr 2025
Binned Group Algebra Factorization for Differentially Private Continual Counting Monika Henzinger Nikita P. Kalinin Jalaj Upadhyay 29 1 0 06 Apr 2025
Investigating Large Language Models in Diagnosing Students' Cognitive Skills in Math Problem-solving Hyoungwook Jin Yoonsu Kim Dongyun Jung Seungju Kim Kiyoon Choi J. Son Juho Kim LRM 62 2 0 01 Apr 2025
Empirical Privacy Variance Yuzheng Hu Fan Wu Ruicheng Xian Yuhang Liu Lydia Zakynthinou Pritish Kamath Chiyuan Zhang David A. Forsyth 62 0 0 16 Mar 2025
Differentially Private Online Federated Learning with Correlated Noise Jiaojiao Zhang Linglingzhi Zhu Mikael Johansson FedML 49 1 0 10 Jan 2025
Data value estimation on private gradients Zijian Zhou Xinyi Xu Daniela Rus Bryan Kian Hsiang Low 74 0 0 22 Dec 2024
DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning using Packed Secret Sharing Alexander Bienstock Ujjwal Kumar Antigoni Polychroniadou FedML 34 0 0 21 Oct 2024
Near Exact Privacy Amplification for Matrix Mechanisms Christopher A. Choquette-Choo Arun Ganesh Saminul Haque Thomas Steinke Abhradeep Thakurta 36 5 0 08 Oct 2024
DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction Xinwei Zhang Zhiqi Bu Mingyi Hong Meisam Razaviyayn 16 4 0 24 Aug 2024
A Hassle-free Algorithm for Private Learning in Practice: Don't Use Tree Aggregation, Use BLTs H. B. McMahan Zheng Xu Yanxiang Zhang FedML 37 5 0 16 Aug 2024
Fine-Tuning Large Language Models with User-Level Differential Privacy Zachary Charles Arun Ganesh Ryan McKenna H. B. McMahan Nicole Mitchell Krishna Pillutla Keith Rush 31 11 0 10 Jul 2024
Continual Counting with Gradual Privacy Expiration Joel Daniel Andersson Monika Henzinger Rasmus Pagh Teresa Anna Steiner Jalaj Upadhyay 43 1 0 06 Jun 2024
Click Without Compromise: Online Advertising Measurement via Per User Differential Privacy Yingtai Xiao Jian Du Shikun Zhang Qiang Yan Danfeng Zhang Daniel Kifer Daniel Kifer 45 2 0 04 Jun 2024
Banded Square Root Matrix Factorization for Differentially Private Model Training Nikita Kalinin Christoph H. Lampert 26 5 0 22 May 2024
Adaptive Data Analysis for Growing Data Neil G. Marchant Benjamin I. P. Rubinstein 30 0 0 22 May 2024
Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy Wei-Ning Chen Berivan Isik Peter Kairouz Albert No Sewoong Oh Zheng Xu 47 3 0 02 May 2024
Teach LLMs to Phish: Stealing Private Information from Language Models Ashwinee Panda Christopher A. Choquette-Choo Zhengming Zhang Yaoqing Yang Prateek Mittal PILM 32 20 0 01 Mar 2024
Auditing Private Prediction Karan Chadha Matthew Jagielski Nicolas Papernot Christopher A. Choquette-Choo Milad Nasr 30 4 0 14 Feb 2024
Momentum Approximation in Asynchronous Private Federated Learning Tao Yu Congzheng Song Jianyu Wang Mona Chitnis FedML 35 1 0 14 Feb 2024
Privacy Amplification for Matrix Mechanisms Christopher A. Choquette-Choo Arun Ganesh Thomas Steinke Abhradeep Thakurta 25 9 0 24 Oct 2023
Correlated Noise Provably Beats Independent Noise for Differentially Private Learning Christopher A. Choquette-Choo Krishnamurthy Dvijotham Krishna Pillutla Arun Ganesh Thomas Steinke Abhradeep Thakurta 22 13 0 10 Oct 2023
Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learning Zachary B. Charles Nicole Mitchell Krishna Pillutla Michael Reneer Zachary Garrett FedML AI4CE 28 28 0 18 Jul 2023
A Unifying Framework for Differentially Private Sums under Continual Observation Monika Henzinger Jalaj Upadhyay Sarvagya Upadhyay FedML 24 14 0 18 Jul 2023
Differentially Private Histogram, Predecessor, and Set Cardinality under Continual Observation Monika Henzinger A. Sricharan Teresa Anna Steiner 23 3 0 17 Jun 2023
A Smooth Binary Mechanism for Efficient Private Continual Observation Joel Daniel Andersson Rasmus Pagh 13 11 0 16 Jun 2023
PLAN: Variance-Aware Private Mean Estimation Martin Aumüller C. Lebeda Boel Nelson Rasmus Pagh FedML 26 4 0 14 Jun 2023
(Amplified) Banded Matrix Factorization: A unified approach to private training Christopher A. Choquette-Choo Arun Ganesh Ryan McKenna H. B. McMahan Keith Rush Abhradeep Thakurta Zheng Xu FedML 23 35 0 13 Jun 2023
Continual Release of Differentially Private Synthetic Data from Longitudinal Data Collections Mark Bun Marco Gaboardi Marcel Neunhoeffer Wanrong Zhang SyDa 19 7 0 13 Jun 2023
Counting Distinct Elements in the Turnstile Model with Differential Privacy under Continual Observation Palak Jain Iden Kalemaj Sofya Raskhodnikova Satchit Sivakumar Adam D. Smith 25 11 0 11 Jun 2023
Differentially Private Stream Processing at Scale Bing Zhang Vadym Doroshenko Peter Kairouz Thomas Steinke Abhradeep Thakurta Zi-Tang Ma Eidan Cohen Himani Apte Jodi Spacek 13 7 0 31 Mar 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
Private Statistical Estimation of Many Quantiles Clément Lalanne Aurélien Garivier Rémi Gribonval 16 5 0 14 Feb 2023
One-shot Empirical Privacy Estimation for Federated Learning Galen Andrew Peter Kairouz Sewoong Oh Alina Oprea H. B. McMahan Vinith M. Suriyakumar FedML 19 32 0 06 Feb 2023
Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy Anastasia Koloskova Ryan McKenna Zachary B. Charles Keith Rush Brendan McMahan 27 8 0 02 Feb 2023
Concurrent Shuffle Differential Privacy Under Continual Observation J. Tenenbaum Haim Kaplan Yishay Mansour Uri Stemmer FedML 28 2 0 29 Jan 2023
Differentially Private Natural Language Models: Recent Advances and Future Directions Lijie Hu Ivan Habernal Lei Shen Di Wang AAML 15 18 0 22 Jan 2023
Differentially Private Adaptive Optimization with Delayed Preconditioners Tian Li Manzil Zaheer Ziyu Liu Sashank J. Reddi H. B. McMahan Virginia Smith 37 10 0 01 Dec 2022
Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning Christopher A. Choquette-Choo H. B. McMahan Keith Rush Abhradeep Thakurta 24 42 0 12 Nov 2022
Almost Tight Error Bounds on Differentially Private Continual Counting Monika Henzinger Jalaj Upadhyay Sarvagya Upadhyay FedML 11 37 0 09 Nov 2022
Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints Virat Shejwalkar Arun Ganesh Rajiv Mathews Om Thakkar Abhradeep Thakurta 15 8 0 04 Oct 2022
Composition of Differential Privacy & Privacy Amplification by Subsampling Thomas Steinke 56 49 0 02 Oct 2022
Constant matters: Fine-grained Complexity of Differentially Private Continual Observation Hendrik Fichtenberger Monika Henzinger Jalaj Upadhyay 29 20 0 23 Feb 2022
The Price of Differential Privacy under Continual Observation Palak Jain Sofya Raskhodnikova Satchit Sivakumar Adam D. Smith 29 51 0 01 Dec 2021
HDMM: Optimizing error of high-dimensional statistical queries under differential privacy Ryan McKenna G. Miklau Michael Hay Ashwin Machanavajjhala 13 20 0 23 Jun 2021
Practical and Private (Deep) Learning without Sampling or Shuffling Peter Kairouz Brendan McMahan Shuang Song Om Thakkar Abhradeep Thakurta Zheng Xu FedML 180 154 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 281 1,812 0 14 Dec 2020