Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining

13 December 2022

Papers citing "Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining"

23 / 23 papers shown

Title
Crowding Out The Noise: Algorithmic Collective Action Under Differential Privacy Rushabh Solanki Meghana Bhange Ulrich Aïvodji Elliot Creager 29 0 0 09 May 2025
Position: LLM Unlearning Benchmarks are Weak Measures of Progress Pratiksha Thaker Shengyuan Hu Neil Kale Yash Maurya Zhiwei Steven Wu Virginia Smith MU 53 10 0 03 Oct 2024
Differentially Private Active Learning: Balancing Effective Data Selection and Privacy Kristian Schwethelm Johannes Kaiser Jonas Kuntzer Mehmet Yigitsoy Daniel Rueckert Georgios Kaissis 34 0 0 01 Oct 2024
Better Locally Private Sparse Estimation Given Multiple Samples Per User Yuheng Ma Ke Jia Hanfang Yang FedML 36 1 0 08 Aug 2024
Noise-Aware Differentially Private Regression via Meta-Learning Ossi Raisa Stratis Markou Matthew Ashman W. Bruinsma Marlon Tobaben Antti Honkela Richard E. Turner 71 1 0 12 Jun 2024
Reconstructing training data from document understanding models Jérémie Dentan Arnaud Paran A. Shabou AAML SyDa 41 1 0 05 Jun 2024
Delving into Differentially Private Transformer Youlong Ding Xueyang Wu Yining Meng Yonggang Luo Hao Wang Weike Pan 31 5 0 28 May 2024
Private Fine-tuning of Large Language Models with Zeroth-order Optimization Xinyu Tang Ashwinee Panda Milad Nasr Saeed Mahloujifar Prateek Mittal 44 18 0 09 Jan 2024
PrivImage: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretraining Kecen Li Chen Gong Zhixiang Li Yuzhong Zhao Xinwen Hou Tianhao Wang 27 10 0 19 Oct 2023
Private Distribution Learning with Public Data: The View from Sample Compression Shai Ben-David Alex Bie C. Canonne Gautam Kamath Vikrant Singhal 40 11 0 11 Aug 2023
Differentially Private Image Classification by Learning Priors from Random Processes Xinyu Tang Ashwinee Panda Vikash Sehwag Prateek Mittal 23 20 0 08 Jun 2023
PILLAR: How to make semi-private learning more effective Francesco Pinto Yaxian Hu Fanny Yang Amartya Sanyal 46 11 0 06 Jun 2023
Privately Customizing Prefinetuning to Better Match User Data in Federated Learning Charlie Hou Hongyuan Zhan Akshat Shrivastava Sida I. Wang S. Livshits Giulia Fanti Daniel Lazar FedML 32 15 0 17 Feb 2023
Extracting Training Data from Diffusion Models Nicholas Carlini Jamie Hayes Milad Nasr Matthew Jagielski Vikash Sehwag Florian Tramèr Borja Balle Daphne Ippolito Eric Wallace DiffM 63 569 0 30 Jan 2023
A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization Ashwinee Panda Xinyu Tang Saeed Mahloujifar Vikash Sehwag Prateek Mittal 40 11 0 08 Dec 2022
On the Impossible Safety of Large AI Models El-Mahdi El-Mhamdi Sadegh Farhadkhani R. Guerraoui Nirupam Gupta L. Hoang Rafael Pinot Sébastien Rouault John Stephan 30 31 0 30 Sep 2022
When the Curious Abandon Honesty: Federated Learning Is Not Private Franziska Boenisch Adam Dziedzic R. Schuster Ali Shahin Shamsabadi Ilia Shumailov Nicolas Papernot FedML AAML 69 181 0 06 Dec 2021
Differentially Private Fine-tuning of Language Models Da Yu Saurabh Naik A. Backurs Sivakanth Gopi Huseyin A. Inan ... Y. Lee Andre Manoel Lukas Wutschitz Sergey Yekhanin Huishuai Zhang 134 346 0 13 Oct 2021
Deduplicating Training Data Makes Language Models Better Katherine Lee Daphne Ippolito A. Nystrom Chiyuan Zhang Douglas Eck Chris Callison-Burch Nicholas Carlini SyDa 242 592 0 14 Jul 2021
Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning Da Yu Huishuai Zhang Wei Chen Tie-Yan Liu FedML SILM 94 110 0 25 Feb 2021
The Pile: An 800GB Dataset of Diverse Text for Language Modeling Leo Gao Stella Biderman Sid Black Laurence Golding Travis Hoppe ... Horace He Anish Thite Noa Nabeshima Shawn Presser Connor Leahy AIMat 253 1,989 0 31 Dec 2020
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 1,814 0 14 Dec 2020
Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware Florian Tramèr Dan Boneh FedML 114 395 0 08 Jun 2018