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

May 24, 2024

Enhancing Learning with Label Differential Privacy by Vector Approximation
Puning Zhao, Rongfei Fan, Huiwen Wu, Qingming Li, Jiafei Wu, Zhe Liu
Differential Privacy Enhanced Learning

May 23, 2024

A Systematic and Formal Study of the Impact of Local Differential Privacy on Fairness: Preliminary Results
Karima Makhlouf, Tamara Stefanovic, Heber H. Arcolezi, Catuscia Palamidessi
Machine Learning Differential Privacy Procedural Fairness Preliminary Study Local Differential Privacy Local Model Privacy Preserving Machine Learning

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

May 21, 2024

Uncertainty quantification by block bootstrap for differentially private stochastic gradient descent
Holger Dette, Carina Graw
Differential Privacy Stochastic Gradient Descent Uncertainty Quantification Local Differential Privacy Private Stochastic Gradient Descent Private Convex Optimization

May 19, 2024

Securing Health Data on the Blockchain: A Differential Privacy and Federated Learning Framework
Daniel Commey, Sena Hounsinou, Garth V. Crosby
Differential Privacy Federated Learning Blockchain Based Platform Healthcare Data Blockchain Network Sensitive Patient

May 16, 2024

The Effect of Quantization in Federated Learning: A R\'enyi Differential Privacy Perspective
Tianqu Kang, Lumin Liu, Hengtao He, Jun Zhang, S. H. Song, Khaled B. Letaief
Differential Privacy Mixed Effect Membership Inference Attack Quantization Operator PRIvacy Leakage Multiplier Free Quantization

May 14, 2024

May 13, 2024

HRNet: Differentially Private Hierarchical and Multi-Resolution Network for Human Mobility Data Synthesization
Shun Takagi, Li Xiong, Fumiyuki Kato, Yang Cao, Masatoshi Yoshikawa
Generative Model Differential Privacy Multi Resolution Human Mobility Mobility Data

May 10, 2024

DP-DyLoRA: Fine-Tuning Transformer-Based Models On-Device under Differentially Private Federated Learning using Dynamic Low-Rank Adaptation
Jie Xu, Karthikeyan Saravanan, Rogier van Dalen, Haaris Mehmood, David Tuckey, Mete Ozay
Differential Privacy Transformer Based Model Low Rank Adaptation Privacy Guarantee Private Federated Learning

May 9, 2024

Age Aware Scheduling for Differentially-Private Federated Learning
Kuan-Yu Lin, Hsuan-Yin Lin, Yu-Pin Hsu, Yu-Chih Huang
Differential Privacy Time Series Three Way Differentially Private Federated Learning

May 8, 2024

Inference With Combining Rules From Multiple Differentially Private Synthetic Datasets
Leila Nombo, Anne-Sophie Charest
Synthetic Data Differential Privacy Scientific Inference Synthetic Data Generation

May 7, 2024

May 6, 2024

May 4, 2024

PrivSGP-VR: Differentially Private Variance-Reduced Stochastic Gradient Push with Tight Utility Bounds
Zehan Zhu, Yan Huang, Xin Wang, Jinming Xu
Differential Privacy Decentralized Learning Private Stochastic Gradient Descent Dp SGD Differential Privacy Noise Gradient Variance

May 3, 2024

FastLloyd: Federated, Accurate, Secure, and Tunable $k$-Means Clustering with Differential Privacy
Abdulrahman Diaa, Thomas Humphries, Florian Kerschbaum
Differential Privacy Federated Prompt Cooperation Secure Aggregation K$ Mean Secure Computation Tunable Slack Mechanism

May 2, 2024

Differential Privacy

Papers

Enhancing Learning with Label Differential Privacy by Vector Approximation

A Systematic and Formal Study of the Impact of Local Differential Privacy on Fairness: Preliminary Results

Naturally Private Recommendations with Determinantal Point Processes

Uncertainty quantification by block bootstrap for differentially private stochastic gradient descent

Securing Health Data on the Blockchain: A Differential Privacy and Federated Learning Framework

The Effect of Quantization in Federated Learning: A R\'enyi Differential Privacy Perspective

Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning

Differentially Private Federated Learning: A Systematic Review

HRNet: Differentially Private Hierarchical and Multi-Resolution Network for Human Mobility Data Synthesization

DP-DyLoRA: Fine-Tuning Transformer-Based Models On-Device under Differentially Private Federated Learning using Dynamic Low-Rank Adaptation

Age Aware Scheduling for Differentially-Private Federated Learning

Inference With Combining Rules From Multiple Differentially Private Synthetic Datasets

Enhancing Scalability of Metric Differential Privacy via Secret Dataset Partitioning and Benders Decomposition

FedSC: Provable Federated Self-supervised Learning with Spectral Contrastive Objective over Non-i.i.d. Data

Unified Locational Differential Privacy Framework

Differentially Private Synthetic Data with Private Density Estimation

PrivSGP-VR: Differentially Private Variance-Reduced Stochastic Gradient Push with Tight Utility Bounds

FastLloyd: Federated, Accurate, Secure, and Tunable $k$-Means Clustering with Differential Privacy

Privacy-aware Berrut Approximated Coded Computing for Federated Learning

1-Diffractor: Efficient and Utility-Preserving Text Obfuscation Leveraging Word-Level Metric Differential Privacy