Differential Privacy

Differential privacy (DP) is a rigorous framework for ensuring data privacy in machine learning by adding carefully calibrated noise to model training processes. Current research focuses on improving the accuracy of DP models, particularly for large-scale training, through techniques like adaptive noise allocation, Kalman filtering for noise reduction, and novel gradient processing methods. This active area of research is crucial for enabling the responsible use of sensitive data in various applications, ranging from healthcare and finance to natural language processing and smart grids, while maintaining strong privacy guarantees.

Papers

August 21, 2023

August 19, 2023

DPMAC: Differentially Private Communication for Cooperative Multi-Agent Reinforcement Learning
Canzhe Zhao, Yanjie Ze, Jing Dong, Baoxiang Wang, Shuai Li
Multi Agent Reinforcement Learning Differential Privacy Privacy Preserving Cooperative Multi Agent Reinforcement Learning Private Text

August 17, 2023

Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models
Phillip Rust, Anders Søgaard
Language Model Differential Privacy Multilingual Language Model Cross Lingual Generalization Language Fairness Training Data Influence

August 7, 2023

Binary Federated Learning with Client-Level Differential Privacy
Lumin Liu, Jun Zhang, Shenghui Song, Khaled B. Letaief
Differential Privacy Privacy Preserving Differential Privacy Guarantee Communication Efficient 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

August 1, 2023

Differential Privacy for Adaptive Weight Aggregation in Federated Tumor Segmentation
Muhammad Irfan Khan, Esa Alhoniemi, Elina Kontio, Suleiman A. Khan, Mojtaba Jafaritadi
Differential Privacy Weight Aggregation Private Aggregation

July 30, 2023

Integrated Private Data Trading Systems for Data Marketplaces
Weidong Li, Mengxiao Zhang, Libo Zhang, Jiamou Liu
Differential Privacy Private Data Data Privacy Data Market

July 28, 2023

Deep Generative Models, Synthetic Tabular Data, and Differential Privacy: An Overview and Synthesis
Conor Hassan, Robert Salomone, Kerrie Mengersen
Generative Model Differential Privacy Synthetic Data Generation Critical Synthesis Tabular Datasets Synthetic Tabular Data Privacy Sensitive

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 25, 2023

July 24, 2023

July 21, 2023

Epsilon*: Privacy Metric for Machine Learning Models
Diana M. Negoescu, Humberto Gonzalez, Saad Eddin Al Orjany, Jilei Yang, Yuliia Lut, Rahul Tandra, Xiaowen Zhang, Xinyi Zheng, Zach Douglas, Vidita Nolkha, Parvez Ahammad, Gennady Samorodnitsky
Machine Learning Model Differential Privacy Privacy Risk Empirical Privacy Model Privacy

July 20, 2023

July 19, 2023