A compressive privacy approach to generalized information bottleneck and privacy funnel problems

DOI10.1016/J.JFRANKLIN.2017.07.002zbMATH Open1396.94106OpenAlexW2735852363MaRDI QIDQ1661460FDOQ1661460

Authors: Y. Aharonov 

Publication date: 16 August 2018

Published in: Journal of the Franklin Institute (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jfranklin.2017.07.002

Recommendations

• Ensuring privacy with constrained additive noise by minimizing Fisher information
• Privacy aware learning
• Extremal mechanisms for local differential privacy
• Differentially private empirical risk minimization
• Universally utility-maximizing privacy mechanisms

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Learning and adaptive systems in artificial intelligence (68T05) Authentication, digital signatures and secret sharing (94A62)

Cites Work

• Fully homomorphic encryption using ideal lattices
• Our Data, Ourselves: Privacy Via Distributed Noise Generation
• Title not available (Why is that?)
• Kernel methods and machine learning

Cited In (2)

• Distributed differentially private average consensus for multi-agent networks by additive functional Laplace noise
• Utility/privacy trade-off as regularized optimal transport

This page was built for publication: A compressive privacy approach to generalized information bottleneck and privacy funnel problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1661460)