DeepAI AI Chat
Log In Sign Up

DPGen: Automated Program Synthesis for Differential Privacy

by   Yuxin Wang, et al.

Differential privacy has become a de facto standard for releasing data in a privacy-preserving way. Creating a differentially private algorithm is a process that often starts with a noise-free (non-private) algorithm. The designer then decides where to add noise, and how much of it to add. This can be a non-trivial process – if not done carefully, the algorithm might either violate differential privacy or have low utility. In this paper, we present DPGen, a program synthesizer that takes in non-private code (without any noise) and automatically synthesizes its differentially private version (with carefully calibrated noise). Under the hood, DPGen uses novel algorithms to automatically generate a sketch program with candidate locations for noise, and then optimize privacy proof and noise scales simultaneously on the sketch program. Moreover, DPGen can synthesize sophisticated mechanisms that adaptively process queries until a specified privacy budget is exhausted. When evaluated on standard benchmarks, DPGen is able to generate differentially private mechanisms that optimize simple utility functions within 120 seconds. It is also powerful enough to synthesize adaptive privacy mechanisms.


page 1

page 2

page 3

page 4


Learning Differentially Private Mechanisms

Differential privacy is a formal, mathematical definition of data privac...

Low Influence, Utility, and Independence in Differential Privacy: A Curious Case of 3 2

We study the relationship between randomized low influence functions and...

Better Differentially Private Approximate Histograms and Heavy Hitters using the Misra-Gries Sketch

We consider the problem of computing differentially private approximate ...

Generalized PTR: User-Friendly Recipes for Data-Adaptive Algorithms with Differential Privacy

The ”Propose-Test-Release” (PTR) framework is a classic recipe for desig...

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

We propose CheckDP, the first automated and integrated approach for prov...

Research Challenges in Designing Differentially Private Text Generation Mechanisms

Accurately learning from user data while ensuring quantifiable privacy g...

Universal Optimality and Robust Utility Bounds for Metric Differential Privacy

We study the privacy-utility trade-off in the context of metric differen...