Privacy Utility Trade

Privacy-utility trade-off research explores methods for releasing or using data while balancing the need to protect sensitive information with the desire to maintain data utility for analysis or model training. Current research focuses on techniques like differential privacy, synthetic data generation (often using diffusion models or autoencoders), and novel algorithms for mitigating membership inference attacks, with a strong emphasis on optimizing the trade-off across various data types (tabular, time-series, graph, etc.) and model architectures. This field is crucial for responsible data sharing and machine learning, enabling the development of privacy-preserving applications while ensuring the continued advancement of data-driven science and technology.

Papers

November 14, 2024

SAFES: Sequential Privacy and Fairness Enhancing Data Synthesis for Responsible AI
Spencer Giddens, Fang Liu
Synthetic Data Differential Privacy Responsible AI Privacy Utility Trade Fair Synthetic

July 9, 2024

Synthetic Data: Revisiting the Privacy-Utility Trade-off
Fatima Jahan Sarmin, Atiquer Rahman Sarkar, Yang Wang, Noman Mohammed
Synthetic Data Privacy Preserving Privacy Utility Differential Privacy Guarantee Privacy Utility Trade

June 3, 2024

Differentially Private Fine-Tuning of Diffusion Models
Yu-Lin Tsai, Yizhe Li, Zekai Chen, Po-Yu Chen, Chia-Mu Yu, Xuebin Ren, Francois Buet-Golfouse
Diffusion Model Differential Privacy Differential Privacy SGD Privacy Utility Trade Private Fine Tuning

May 22, 2024

Naturally Private Recommendations with Determinantal Point Processes
Jack Fitzsimons, Agustín Freitas Pasqualini, Robert Pisarczyk, Dmitrii Usynin
Differential Privacy Determinantal Point Process Privacy Utility Trade Differential Privacy Constraint Randomized Mechanism

April 7, 2024

Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4
Bishwas Mandal, George Amariucai, Shuangqing Wei
Large Language Model GPT 4 Tabular Data Task Utility Privacy Utility Adversarial Method Privacy Utility Trade Adversarial Optimization

April 4, 2024

A Comparative Analysis of Word-Level Metric Differential Privacy: Benchmarking The Privacy-Utility Trade-off
Stephen Meisenbacher, Nihildev Nandakumar, Alexandra Klymenko, Florian Matthes
Natural Language Processing Differential Privacy Comparative Study Privacy Utility Trade

March 2, 2024

An Efficient Difference-of-Convex Solver for Privacy Funnel
Teng-Hui Huang, Hesham El Gamal
Variational Inference Convex Optimization Privacy Utility Trade Hybrid Solver Minimization Algorithm Privacy Funnel

October 31, 2023

Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks
Jiayuan Ye, Zhenyu Zhu, Fanghui Liu, Reza Shokri, Volkan Cevher
Neural Network New Initialization Data Leakage Benign Over Parameterization Privacy Utility Trade

October 27, 2023

$\alpha$-Mutual Information: A Tunable Privacy Measure for Privacy Protection in Data Sharing
MirHamed Jafarzadeh Asl, Mohammadhadi Shateri, Fabrice Labeau
Mutual Information Data Sharing Privacy Utility Trade Data Release User Configurable Privacy Defense

October 17, 2023

Locally Differentially Private Graph Embedding
Zening Li, Rong-Hua Li, Meihao Liao, Fusheng Jin, Guoren Wang
Graph Data Local Differential Privacy Real World Graph Privacy Utility Trade Personalized Pagerank Private Graph

September 15, 2023

Evaluating the Impact of Local Differential Privacy on Utility Loss via Influence Functions
Alycia N. Carey, Minh-Hao Van, Xintao Wu
Differential Privacy Global Impact Local Differential Privacy Influence Function Privacy Utility Trade Privacy Parameter

September 8, 2023

Robust Representation Learning for Privacy-Preserving Machine Learning: A Multi-Objective Autoencoder Approach
Sofiane Ouaari, Ali Burak Ünal, Mete Akgün, Nico Pfeifer
Machine Learning Differential Privacy Homomorphic Encryption Privacy Preserving Machine Learning Robust Representation Learning Privacy Utility Trade

July 4, 2023

Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction
Zitao Chen, Karthik Pattabiraman
Membership Inference Attack Privacy Risk Good Thing Privacy Protection Privacy Utility Trade Membership Privacy Overconfidence Problem

April 10, 2023

Analysing Fairness of Privacy-Utility Mobility Models
Yuting Zhan, Hamed Haddadi, Afra Mashhadi
Fairness Metric Privacy Utility Privacy Utility Trade Fairness Analysis Fairness Estimation

March 7, 2023

adaPARL: Adaptive Privacy-Aware Reinforcement Learning for Sequential-Decision Making Human-in-the-Loop Systems
Mojtaba Taherisadr, Stelios Andrew Stavroulakis, Salma Elmalaki
Reinforcement Learning Human in the Loop Privacy Utility Privacy Utility Trade

February 24, 2023

Membership Inference Attacks against Synthetic Data through Overfitting Detection
Boris van Breugel, Hao Sun, Zhaozhi Qian, Mihaela van der Schaar
Synthetic Data Membership Inference Attack Model Overfitting Privacy Attack Privacy Utility Trade Density Model

November 21, 2022

Private Ad Modeling with DP-SGD
Carson Denison, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Krishna Giri Narra, Amer Sinha, Avinash V Varadarajan, Chiyuan Zhang
Private Stochastic Private Model Privacy Utility Trade

September 8, 2022

A Framework for Evaluating Privacy-Utility Trade-off in Vertical Federated Learning
Yan Kang, Jiahuan Luo, Yuanqin He, Xiaojin Zhang, Lixin Fan, Qiang Yang
New Framework Privacy Preserving Vertical Federated Learning Privacy Attack Privacy Utility Privacy Utility Trade Label Inference Attack

August 9, 2022

Privacy-Aware Adversarial Network in Human Mobility Prediction
Yuting Zhan, Hamed Haddadi, Afra Mashhadi
Mobility Data Private Training Privacy Utility Trade Identification Risk Human Mobility Prediction Adversarial Privacy

May 27, 2022

A Blessing of Dimensionality in Membership Inference through Regularization
Jasper Tan, Daniel LeJeune, Blake Mason, Hamid Javadi, Richard G. Baraniuk
Generalization Performance Membership Inference Attack Data Dimensionality Membership Inference Overparametrization Bound Privacy Utility Trade Blessing Generation

Privacy Utility Trade

Papers

SAFES: Sequential Privacy and Fairness Enhancing Data Synthesis for Responsible AI

Synthetic Data: Revisiting the Privacy-Utility Trade-off

Differentially Private Fine-Tuning of Diffusion Models

Naturally Private Recommendations with Determinantal Point Processes

Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4

A Comparative Analysis of Word-Level Metric Differential Privacy: Benchmarking The Privacy-Utility Trade-off

An Efficient Difference-of-Convex Solver for Privacy Funnel

Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks

$\alpha$-Mutual Information: A Tunable Privacy Measure for Privacy Protection in Data Sharing

Locally Differentially Private Graph Embedding

Evaluating the Impact of Local Differential Privacy on Utility Loss via Influence Functions

Robust Representation Learning for Privacy-Preserving Machine Learning: A Multi-Objective Autoencoder Approach

Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction

Analysing Fairness of Privacy-Utility Mobility Models

adaPARL: Adaptive Privacy-Aware Reinforcement Learning for Sequential-Decision Making Human-in-the-Loop Systems

Membership Inference Attacks against Synthetic Data through Overfitting Detection

Private Ad Modeling with DP-SGD

A Framework for Evaluating Privacy-Utility Trade-off in Vertical Federated Learning

Privacy-Aware Adversarial Network in Human Mobility Prediction

A Blessing of Dimensionality in Membership Inference through Regularization