Information-Theoretic foundations of differential privacy

Authors:
Darakhshan J. Mir
Affiliations:
Rutgers University, Piscataway, NJ
Venue:
FPS'12 Proceedings of the 5th international conference on Foundations and Practice of Security
Year:
2012

Citing 11
Cited 0

Elements of Information Theory (Wiley Series in Telecommunications and Signal Processing)

Elements of Information Theory (Wiley Series in Telecommunications and Signal Processing)
Mechanism Design via Differential Privacy

FOCS '07 Proceedings of the 48th Annual IEEE Symposium on Foundations of Computer Science
From t-Closeness-Like Privacy to Postrandomization via Information Theory

IEEE Transactions on Knowledge and Data Engineering
The Limits of Two-Party Differential Privacy

FOCS '10 Proceedings of the 2010 IEEE 51st Annual Symposium on Foundations of Computer Science
An information theoretic approach for privacy metrics

Transactions on Data Privacy
Information-Theoretic Bounds for Differentially Private Mechanisms

CSF '11 Proceedings of the 2011 IEEE 24th Computer Security Foundations Symposium
Differential privacy

ICALP'06 Proceedings of the 33rd international conference on Automata, Languages and Programming - Volume Part II
Calibrating noise to sensitivity in private data analysis

TCC'06 Proceedings of the Third conference on Theory of Cryptography
An Information-Theoretic Approach to Inference Attacks on Random Data Perturbation and a Related Privacy Measure

IEEE Transactions on Information Theory
Differentially-private learning and information theory

Proceedings of the 2012 Joint EDBT/ICDT Workshops
Differential privacy: on the trade-off between utility and information leakage

FAST'11 Proceedings of the 8th international conference on Formal Aspects of Security and Trust

Quantified Score

Hi-index	0.00

Visualization

Abstract

We examine the information-theoretic foundations of the increasingly popular notion of differential privacy. We establish a connection between differential private mechanisms and the rate-distortion framework. Additionally, we also show how differentially private distributions arise out of the application of the Maximum Entropy Principle. This helps us locate differential privacy within the wider framework of information-theory and helps formalize some intuitive aspects of our understanding of differential privacy.