Deciding Accuracy of Differential Privacy Schemes

by   Gilles Barthe, et al.

Differential privacy is a mathematical framework for developing statistical computations with provable guarantees of privacy and accuracy. In contrast to the privacy component of differential privacy, which has a clear mathematical and intuitive meaning, the accuracy component of differential privacy does not have a generally accepted definition; accuracy claims of differential privacy algorithms vary from algorithm to algorithm and are not instantiations of a general definition. We identify program discontinuity as a common theme in existing ad hoc definitions and introduce an alternative notion of accuracy parametrized by, what we call, – the of an input x w.r.t., a deterministic computation f and a distance d, is the minimal distance d(x,y) over all y such that f(y)≠ f(x). We show that our notion of accuracy subsumes the definition used in theoretical computer science, and captures known accuracy claims for differential privacy algorithms. In fact, our general notion of accuracy helps us prove better claims in some cases. Next, we study the decidability of accuracy. We first show that accuracy is in general undecidable. Then, we define a non-trivial class of probabilistic computations for which accuracy is decidable (unconditionally, or assuming Schanuel's conjecture). We implement our decision procedure and experimentally evaluate the effectiveness of our approach for generating proofs or counterexamples of accuracy for common algorithms from the literature.


page 1

page 2

page 3

page 4


Automated Methods for Checking Differential Privacy

Differential privacy is a de facto standard for statistical computations...

Author Obfuscation Using Generalised Differential Privacy

The problem of obfuscating the authorship of a text document has receive...

Capacity Bounded Differential Privacy

Differential privacy, a notion of algorithmic stability, is a gold stand...

Quantum Differential Privacy: An Information Theory Perspective

Differential privacy has been an exceptionally successful concept when i...

Toward Detecting Violations of Differential Privacy

The widespread acceptance of differential privacy has led to the publica...

On Privacy Notion in Anonymous Communication

Many anonymous communication networks (ACNs) with different privacy goal...

A unified view on differential privacy and robustness to adversarial examples

This short note highlights some links between two lines of research with...

Please sign up or login with your details

Forgot password? Click here to reset