Private Datasets

Private datasets present a significant challenge in leveraging data for machine learning while safeguarding sensitive information. Current research focuses on developing privacy-preserving techniques, such as differential privacy, federated learning, and secure multi-party computation, often employing generative models (like normalizing flows) and advanced algorithms (e.g., zeroth-order optimization) to enable collaborative model training and inference without direct data sharing. These advancements are crucial for unlocking the potential of sensitive data in various fields, including healthcare, finance, and agriculture, while mitigating privacy risks and promoting responsible data usage. The ultimate goal is to balance the utility of data-driven insights with robust protection of individual privacy.

Papers

July 25, 2023

Accuracy Improvement in Differentially Private Logistic Regression: A Pre-training Approach
Mohammad Hoseinpour, Milad Hoseinpour, Ali Aghagolzadeh
Differential Privacy Pre Training Accuracy Improvement Private Datasets Private Linear Regression Inherent Privacy

June 8, 2023

Privacy- and Utility-Preserving NLP with Anonymized Data: A case study of Pseudonymization
Oleksandr Yermilov, Vipul Raheja, Artem Chernodub
Case Study NLP Field NLP Task Privacy Policy Private Datasets Anonymization Technique Anonymised Data

May 24, 2023

Differentially Private Synthetic Data via Foundation Model APIs 1: Images
Zinan Lin, Sivakanth Gopi, Janardhan Kulkarni, Harsha Nori, Sergey Yekhanin
Synthetic Data Foundation Model Private Data Private Datasets

May 23, 2023

Selective Pre-training for Private Fine-tuning
Da Yu, Sivakanth Gopi, Janardhan Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang
Language Model Private Learning Private Datasets Private Fine Tuning

March 31, 2023

PEOPL: Characterizing Privately Encoded Open Datasets with Public Labels
Homa Esfahanizadeh, Adam Yala, Rafael G. L. D'Oliveira, Andrea J. D. Jaba, Victor Quach, Ken R. Duffy, Tommi S. Jaakkola, Vinod Vaikuntanathan, Manya Ghobadi, Regina Barzilay, Muriel Médard
Data Encoding Manual Label Private Datasets Open Dataset Information Leakage Deep Random Neural Network

February 11, 2023

Differentially Private Normalizing Flows for Density Estimation, Data Synthesis, and Variational Inference with Application to Electronic Health Records
Bingyue Su, Yu Wang, Daniele E. Schiavazzi, Fang Liu
Synthetic Data Differential Privacy Variational Inference Normalizing Flow Electronic Health Record Density Estimation Data Synthesis Private Datasets

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

November 6, 2022

Confidence-Ranked Reconstruction of Census Microdata from Published Statistics
Travis Dick, Cynthia Dwork, Michael Kearns, Terrance Liu, Aaron Roth, Giuseppe Vietri, Zhiwei Steven Wu
Differential Privacy Full State Reconstruction Reconstruction Attack Private Datasets Data Reconstruction Attack Census Data

October 6, 2022

June 21, 2022

The Privacy Onion Effect: Memorization is Relative
Nicholas Carlini, Matthew Jagielski, Chiyuan Zhang, Nicolas Papernot, Andreas Terzis, Florian Tramer
PRIvacy Leakage Privacy Guarantee Limited Memorization Privacy Attack Private Datasets Privacy Amplification Privacy Enhancing Technology

June 14, 2022

Self-Supervised Pretraining for Differentially Private Learning
Arash Asadian, Evan Weidner, Lei Jiang
Deep Learning Differential Privacy Self Supervised Pretraining Private Learning Private Datasets

May 25, 2022

Additive Logistic Mechanism for Privacy-Preserving Self-Supervised Learning
Yunhao Yang, Parham Gohari, Ufuk Topcu
Self Supervised Learning Membership Inference Attack Privacy Attack Private Datasets Differential Privacy Mechanism Privacy Preserving Training

March 22, 2022

Mixed Differential Privacy in Computer Vision
Aditya Golatkar, Alessandro Achille, Yu-Xiang Wang, Aaron Roth, Michael Kearns, Stefano Soatto
Computer Vision Differential Privacy Privacy Guarantee Private Algorithm Private Datasets Private Fine Tuning

February 7, 2022

Locally Differentially Private Distributed Deep Learning via Knowledge Distillation
Di Zhuang, Mingchen Li, J. Morris Chang
Deep Learning Knowledge Distillation Local Differential Privacy Private Datasets

February 6, 2022

BEAS: Blockchain Enabled Asynchronous & Secure Federated Machine Learning
Arup Mondal, Harpreet Virk, Debayan Gupta
Federated Learning Blockchain Based Platform Differential Privacy Guarantee Private Datasets Model Poisoning Attack Data Reconstruction Attack Asynchronous Architecture

January 24, 2022

Post-processing of Differentially Private Data: A Fairness Perspective
Keyu Zhu, Ferdinando Fioretto, Pascal Van Hentenryck
Differential Privacy Private Data Post Processing Private Datasets Differential Analysis