Privacy Guarantee

Privacy guarantees in machine learning aim to enable collaborative model training and data analysis while protecting sensitive individual information. Current research focuses on enhancing differential privacy mechanisms, particularly within federated learning frameworks, employing techniques like noise addition, gradient clipping, and model compression to achieve a balance between privacy and model utility. These advancements are crucial for responsible data usage in various fields, including healthcare, finance, and social sciences, facilitating the development of powerful models while mitigating privacy risks. Active research also explores alternative approaches like homomorphic encryption and synthetic data generation to provide robust privacy protections.

Papers

February 14, 2024

Why Does Differential Privacy with Large Epsilon Defend Against Practical Membership Inference Attacks?
Andrew Lowy, Zhuohang Li, Jing Liu, Toshiaki Koike-Akino, Kieran Parsons, Ye Wang
Differential Privacy Membership Inference Attack Privacy Guarantee Worst Case Privacy Parameter

February 10, 2024

Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off
Yuecheng Li, Tong Wang, Chuan Chen, Jian Lou, Bin Chen, Lei Yang, Zibin Zheng
Differential Privacy Extension Study PRIvacy Leakage Privacy Guarantee Private Federated Learning Client Collaboration Utility Privacy Trade

February 5, 2024

Fairness and Privacy Guarantees in Federated Contextual Bandits
Sambhav Solanki, Shweta Jain, Sujit Gujar
Procedural Fairness Privacy Guarantee Contextual Multi Armed Bandit Fairness Regret

January 30, 2024

Personalized Differential Privacy for Ridge Regression
Krishna Acharya, Franziska Boenisch, Rakshit Naidu, Juba Ziani
Differential Privacy Privacy Guarantee Ridge Regression Privacy Accuracy

January 26, 2024

An Algorithm for Streaming Differentially Private Data
Girish Kumar, Thomas Strohmer, Roman Vershynin
Differential Privacy Practical Algorithm Synthetic Data Generation Data Generation Private Data Privacy Guarantee Automatic Counting Online Streaming

January 11, 2024

Qrlew: Rewriting SQL into Differentially Private SQL
Nicolas Grislain, Paul Roussel, Victoria de Sainte Agathe
Privacy Guarantee Differentially Private SQL Query Private Data Analysis Data Type

December 11, 2023

Classification with Partially Private Features
Zeyu Shen, Anilesh Krishnaswamy, Janardhan Kulkarni, Kamesh Munagala
Classification Code Differential Privacy Private Data Privacy Guarantee Private Linear Regression Private Feature

December 10, 2023

QMGeo: Differentially Private Federated Learning via Stochastic Quantization with Mixed Truncated Geometric Distribution
Zixi Wang, M. Cenk Gursoy
Differential Privacy Privacy Guarantee Private Federated Learning Product Quantization Stochastic Quantization

December 7, 2023

On the Impact of Multi-dimensional Local Differential Privacy on Fairness
Karima Makhlouf, Heber H. Arcolezi, Sami Zhioua, Ghassen Ben Brahim, Catuscia Palamidessi
Global Impact Procedural Fairness Privacy Guarantee Local Differential Privacy Privacy Preservation Sensitive Attribute

November 24, 2023

Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
Xinwei Zhang, Zhiqi Bu, Zhiwei Steven Wu, Mingyi Hong
Differential Privacy Absolute Stance Bias Error Feedback Privacy Guarantee Private Stochastic Gradient Descent Gradient Clipping

November 3, 2023

Automating Governing Knowledge Commons and Contextual Integrity (GKC-CI) Privacy Policy Annotations with Large Language Models
Jake Chanenson, Madison Pickering, Noah Apthorpe
Ground Truth Privacy Guarantee Contextual Integrity

October 10, 2023

Statistical properties and privacy guarantees of an original distance-based fully synthetic data generation method
Rémy Chapelle, Bruno Falissard
Synthetic Data Synthetic Data Generation Synthetic Dataset Privacy Guarantee Statistical Property

September 28, 2023

Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey
Lea Demelius, Roman Kern, Andreas Trügler
Differential Privacy Comprehensive Survey Recent Advance Privacy Guarantee Privacy Utility Private Model Private Generative Model

September 7, 2023

Byzantine-Robust Federated Learning with Variance Reduction and Differential Privacy
Zikai Zhang, Rui Hu
Differential Privacy Privacy Guarantee Variance Reduction Privacy Analysis Byzantine Attack Byzantine Robust Federated Learning Client Level Differential Privacy

August 2, 2023

Causal Inference with Differentially Private (Clustered) Outcomes
Adel Javanmard, Vahab Mirrokni, Jean Pouget-Abadie
Differential Privacy Causal Inference Privacy Guarantee Multiple Outcome Private Mechanism

July 26, 2023

Flexible Differentially Private Vertical Federated Learning with Adaptive Feature Embeddings
Yuxi Mi, Hongquan Liu, Yewei Xia, Yiheng Sun, Jihong Guan, Shuigeng Zhou
Differential Privacy Task Utility Vertical Federated Learning Privacy Guarantee Data Privacy Adaptive Representation

July 20, 2023

Private Federated Learning with Autotuned Compression
Enayat Ullah, Christopher A. Choquette-Choo, Peter Kairouz, Sewoong Oh
Differential Privacy Privacy Guarantee Secure Aggregation Private Federated Learning High Compression

July 14, 2023

Population Expansion for Training Language Models with Private Federated Learning
Tatsuki Koga, Congzheng Song, Martin Pelikan, Mona Chitnis
Language Model Domain Adaptation Differential Privacy Privacy Guarantee Private Federated Learning

July 6, 2023

Quantum Solutions to the Privacy vs. Utility Tradeoff
Sagnik Chatterjee, Vyacheslav Kungurtsev
Differential Privacy Membership Inference Attack Privacy Policy Privacy Guarantee Quantum Gate Cryptographic Primitive Utility Tradeoff

June 12, 2023

AnoFel: Supporting Anonymity for Privacy-Preserving Federated Learning
Ghada Almashaqbeh, Zahra Ghodsi
Privacy Guarantee Consistent Anonymization Effect