CheckDP: An Automated and Integrated Approach for Proving Differential Privacy or Finding Precise Counterexamples

08/17/2020
by   Yuxin Wang, et al.
0

We propose CheckDP, the first automated and integrated approach for proving or disproving claims that a mechanism is differentially private. CheckDP can find counterexamples for mechanisms with subtle bugs for which prior counterexample generators have failed. Furthermore, it was able to automatically generate proofs for correct mechanisms for which no formal verification was reported before. CheckDP is built on static program analysis, allowing it to be more efficient and more precise in catching infrequent events than existing counterexample generators (which run mechanisms hundreds of thousands of times to estimate their output distribution). Moreover, its sound approach also allows automatic verification of correct mechanisms. When evaluated on standard benchmarks and newer privacy mechanisms, CheckDP generates proofs (for correct mechanisms) and counterexamples (for incorrect mechanisms) within 70 seconds without any false positives or false negatives.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/15/2021

DPGen: Automated Program Synthesis for Differential Privacy

Differential privacy has become a de facto standard for releasing data i...
research
10/08/2020

Testing Differential Privacy with Dual Interpreters

Applying differential privacy at scale requires convenient ways to check...
research
07/10/2023

RényiTester: A Variational Approach to Testing Differential Privacy

Governments and industries have widely adopted differential privacy as a...
research
02/15/2023

Tight Auditing of Differentially Private Machine Learning

Auditing mechanisms for differential privacy use probabilistic means to ...
research
08/04/2020

Verifying Pufferfish Privacy in Hidden Markov Models

Pufferfish is a Bayesian privacy framework for designing and analyzing p...
research
03/28/2019

Proving Differential Privacy with Shadow Execution

Recent work on formal verification of differential privacy shows a trend...
research
09/28/2020

A Large Scale Benchmark and an Inclusion-Based Algorithm for Continuous Collision Detection

We introduce a large scale benchmark for continuous collision detection ...

Please sign up or login with your details

Forgot password? Click here to reset