Certified private data release for sparse Lipschitz functions

2023/02/19 by Konstantin Donhauser, Johan Lokna, Donhauser, Konstantin +9 · 2 citations
Computer Science · Engineering · #Cryptography and Data Security #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Privacy-Preserving Technologies in Data #Wireless Communication Security Techniques

paper · pdf · doi:10.48550/arxiv.2302.09680

openalex publication_date 2023/02/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

As machine learning has become more relevant for everyday applications, a natural requirement is the protection of the privacy of the training data. When the relevant learning questions are unknown in advance, or hyper-parameter tuning plays a central role, one solution is to release a differentially private synthetic data set that leads to similar conclusions as the original training data. In this work, we introduce an algorithm that enjoys fast rates for the utility loss for sparse Lipschitz queries. Furthermore, we show how to obtain a certificate for the utility loss for a large class of algorithms.

Cited by

• Private Evolution Converges
• Robust Privacy: Inference-Stage Privacy through Certified Robustness

Related

• Testing Lipschitz Property over Product Distribution and its Applications to Statistical Data Privacy
• Renyi Differential Privacy of Propose-Test-Release and Applications to Private and Robust Machine Learning
• Certification for Differentially Private Prediction in Gradient-Based Training
• Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds
• Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data