Private Data

Private data research focuses on enabling the use of sensitive information for machine learning and other data analysis tasks while rigorously protecting individual privacy. Current efforts concentrate on developing differentially private algorithms, federated learning frameworks (including variations like vertical federated learning and split learning), and techniques for synthetic data generation to mitigate privacy risks associated with model training and data sharing. These advancements are crucial for unlocking the potential of large datasets in various fields, from healthcare and finance to social sciences, while addressing ethical and legal concerns surrounding data privacy.

Papers

February 19, 2023

Why Is Public Pretraining Necessary for Private Model Training?
Arun Ganesh, Mahdi Haghifam, Milad Nasr, Sewoong Oh, Thomas Steinke, Om Thakkar, Abhradeep Thakurta, Lun Wang
Transfer Learning Model Training Private Data Privacy Utility Private Model Training

February 17, 2023

Privately Customizing Prefinetuning to Better Match User Data in Federated Learning
Charlie Hou, Hongyuan Zhan, Akshat Shrivastava, Sid Wang, Aleksandr Livshits, Giulia Fanti, Daniel Lazar
Private Data Parameter Efficient Finetuning Federated Data User Data

January 9, 2023

Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregation
Franziska Boenisch, Adam Dziedzic, Roei Schuster, Ali Shahin Shamsabadi, Ilia Shumailov, Nicolas Papernot
Differential Privacy Federated Learning Private Data Secure Aggregation Privacy Enhancing Technology Data Reconstruction

January 7, 2023

k-Means SubClustering: A Differentially Private Algorithm with Improved Clustering Quality
Devvrat Joshi, Janvi Thakkar
Differential Privacy K Mean Private Data Private Algorithm Exponential Mechanism Private Clustering Clustering Performance

December 23, 2022

Offline Reinforcement Learning for Human-Guided Human-Machine Interaction with Private Information
Zuyue Fu, Zhengling Qi, Zhuoran Yang, Zhaoran Wang, Lan Wang
Offline Reinforcement Learning Policy Evaluation Private Data Human Machine Interaction Policy Algorithm

November 28, 2022

Decentralized Learning with Multi-Headed Distillation
Andrey Zhmoginov, Mark Sandler, Nolan Miller, Gus Kristiansen, Max Vladymyrov
Decentralized Learning Private Data Decentralized FL Data Balancing Communication Graph Distillation Paradigm Decentralized Knowledge Distillation

October 24, 2022

Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano
Chuan Guo, Alexandre Sablayrolles, Maziar Sanjabi
Machine Learning Differential Privacy Private Data Explanatory Inference Data Reconstruction Attack Multiple Hypothesis Testing Instructional Design Privacy Leakage

October 22, 2022

Federated Calibration and Evaluation of Binary Classifiers
Graham Cormode, Igor Markov
Differential Privacy Global Evaluation Private Data Local Differential Privacy Secure Aggregation Binary Classifier Privacy Model Federated Hyperparameter

October 9, 2022

Performances of Symmetric Loss for Private Data from Exponential Mechanism
Jing Bi, Vorapong Suppakitpaisarn
Native Robustness Private Data Private Learning Exponential Mechanism Symmetric Loss

October 6, 2022

DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharing
Jiawei Shao, Yuchang Sun, Songze Li, Jun Zhang
Federated Learning Private Data Private Datasets Client Collaboration Local Gradient

September 13, 2022

Concealing Sensitive Samples against Gradient Leakage in Federated Learning
Jing Wu, Munawar Hayat, Mingyi Zhou, Mehrtash Harandi
Sensitive Data Private Data Model Inversion Attack Gradient Information Gradient Leakage

August 31, 2022

Non-readily identifiable data collaboration analysis for multiple datasets including personal information
Akira Imakura, Tetsuya Sakurai, Yukihiko Okada, Tomoya Fujii, Teppei Sakamoto, Hiroyuki Abe
Private Data Medical Datasets Personal Information Data Fusion Data Collaboration

August 26, 2022

Abnormal Local Clustering in Federated Learning
Jihwan Won
Private Data Local Model Federated Image Classification Evident Abnormality Local Clustering Minimum Sum of Square Clustering

August 24, 2022

On the Design of Privacy-Aware Cameras: a Study on Deep Neural Networks
Marcela Carvalho, Oussama Ennaffi, Sylvain Chateau, Samy Ait Bachir
Deep Neural Network Product Design Study Feature Private Data Surveillance Camera Focus Blur

August 16, 2022

Collaborative causal inference on distributed data
Yuji Kawamata, Ryoki Motai, Yukihiko Okada, Akira Imakura, Tetsuya Sakurai
Raw Data Causal Inference Private Data Causal Direction Intermediate Representation Data Collaboration

August 12, 2022

Is Your Model Sensitive? SPeDaC: A New Benchmark for Detecting and Classifying Sensitive Personal Data
Gaia Gambarelli, Aldo Gangemi, Rocco Tripodi
New Benchmark Data Detection Sensitive Data Private Data Personal Information Public Model Information Detection

August 5, 2022

DP$^2$-VAE: Differentially Private Pre-trained Variational Autoencoders
Dihong Jiang, Guojun Zhang, Mahdi Karami, Xi Chen, Yunfeng Shao, Yaoliang Yu
Variational Autoencoders Private Data Lung VAE Private Generative Model Text Privatization Private Variational

August 2, 2022

Differentially Private Vertical Federated Clustering
Zitao Li, Tianhao Wang, Ninghui Li
Private Data Private Clustering

June 21, 2022

Differentially Private Maximal Information Coefficients
John Lazarsfeld, Aaron Johnson, Emmanuel Adeniran
Differential Privacy Mutual Information Private Data Private INFORMATION RETRIEVAL

June 18, 2022

Secure Embedding Aggregation for Federated Representation Learning
Jiaxiang Tang, Jinbao Zhu, Songze Li, Lichao Sun
Jina Embeddings Private Data Data Aggregation Secure Approach Representation Learning Framework Local Embeddings Federated Representation Learning