Non Private

Research on differentially private machine learning aims to train accurate models while rigorously protecting individual data privacy. Current efforts focus on improving the privacy-utility trade-off through techniques like differentially private feature selection, adapting algorithms for various model architectures (including Mixture of Experts and large language models), and developing efficient methods for private inference and model compression. These advancements are crucial for enabling responsible use of sensitive data in diverse applications, ranging from healthcare to natural language processing, while addressing the inherent challenges of balancing privacy with model accuracy.

Papers

October 15, 2024

Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning
Fengyu Gao, Ruida Zhou, Tianhao Wang, Cong Shen, Jing Yang
LeArning Abstract Context Learning Different Context Differential Privacy Guarantee Private Datasets Non Private

August 20, 2024

Feature Selection from Differentially Private Correlations
Ryan Swope, Amol Khanna, Philip Doldo, Saptarshi Roy, Edward Raff
Differential Privacy High Dimensional Feature Selection Private Mean Estimation Non Private

February 11, 2024

September 9, 2023

Approximating ReLU on a Reduced Ring for Efficient MPC-based Private Inference
Kiwan Maeng, G. Edward Suh
High Efficiency Privacy Sensitive Private Inference Non Private Multi Party Computation

August 31, 2023

Pure Differential Privacy for Functional Summaries via a Laplace-like Process
Haotian Lin, Matthew Reimherr
Differential Privacy Simple Function Output Space Laplace Approximation Non Private Infinite Dimensional

June 1, 2023

Better Private Linear Regression Through Better Private Feature Selection
Travis Dick, Jennifer Gillenwater, Matthew Joseph
Good Better Private Linear Regression Non Private Rank Correlation

May 28, 2023

Training Private Models That Know What They Don't Know
Stephan Rabanser, Anvith Thudi, Abhradeep Thakurta, Krishnamurthy Dvijotham, Nicolas Papernot
Differential Privacy Selective Prediction Non Private Differential Privacy Constraint Private Learning Algorithm

May 24, 2023

Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models
Haonan Duan, Adam Dziedzic, Nicolas Papernot, Franziska Boenisch
Large Language Model Membership Inference Attack Private Algorithm Private Gradient Feather Flock Non Private

February 21, 2023

FedSDG-FS: Efficient and Secure Feature Selection for Vertical Federated Learning
Anran Li, Hongyi Peng, Lan Zhang, Jiahui Huang, Qing Guo, Han Yu, Yang Liu
Feature Selection Homomorphic Encryption Vertical Federated Learning Feature Importance Gaussian Model Federated Stochastic Non Private

February 2, 2023

On the Efficacy of Differentially Private Few-shot Image Classification
Marlon Tobaben, Aliaksandra Shysheya, John Bronskill, Andrew Paverd, Shruti Tople, Santiago Zanella-Beguelin, Richard E Turner, Antti Honkela
Shot Image Classification Differentially Private Private Datasets Differential Analysis Non Private

December 13, 2022

Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
Florian Tramèr, Gautam Kamath, Nicholas Carlini
Differential Privacy Product Specific Position Information Private Learning Crucial Consideration Large Scale Pretraining Private Machine Learning Non Private

July 1, 2022

When Does Differentially Private Learning Not Suffer in High Dimensions?
Xuechen Li, Daogao Liu, Tatsunori Hashimoto, Huseyin A. Inan, Janardhan Kulkarni, Yin Tat Lee, Abhradeep Guha Thakurta
High Dimension Private Learning Private Fine Tuning Non Private Private Convex

June 3, 2022

Differentially Private Model Compression
Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin A Inan, Lukas Wutschitz, Janardhan Kulkarni
Differential Privacy BERT Model Model Compression Large Pre Trained Language Model Non Private

May 6, 2022

December 15, 2021

One size does not fit all: Investigating strategies for differentially-private learning across NLP tasks
Manuel Senge, Timour Igamberdiev, Ivan Habernal
NLP Task Privacy Preserving General Strategy Private Stochastic Size Matter Differentially Private Privacy Enhancing Technology Non Private