Classification under local differential privacy

2019/12/10 by Thomas B. Berrett, Thomas Berrett, Berrett, Thomas +2
Computer Science · Mathematics · Social Sciences · #62G08 #Cryptography and Data Security #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (stat.ML) #Methodology (stat.ME) #Privacy, Security, and Data Protection #Privacy-Preserving Technologies in Data #Statistics Theory (math.ST) #math.ST #msc:62G08 #stat.ME #stat.ML #stat.TH

paper · pdf · doi:10.48550/arxiv.1912.04629

12 pages

arxiv created 2019/12/10 · openalex publication_date 2019/12/10 · arxiv updated 2019/12/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We consider the binary classification problem in a setup that preserves the privacy of the original sample. We provide a privacy mechanism that is locally differentially private and then construct a classifier based on the private sample that is universally consistent in Euclidean spaces. Under stronger assumptions, we establish the minimax rates of convergence of the excess risk and see that they are slower than in the case when the original sample is available.

Citations

• Calibrating Noise to Sensitivity in Private Data Analysis
• Fast learning rates for plug-in classifiers
• Transfer Learning for Nonparametric Classification: Minimax Rate and Adaptive Classifier

Related

• Classification Under Local Differential Privacy with Model Reversal and Model Averaging
• Locally Differentially Private Naive Bayes Classification
• Classification with Partially Private Features
• Minimax Optimal Two-Sample Testing under Local Differential Privacy
• Local Differential Privacy Is Equivalent to Contraction of E_γ-Divergence