Work

DPGen: Automated Program Synthesis for Differential Privacy

Year: 2021

Type: conference-paper

Abstract: 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.

Source: ACM SIGSAC Conference on Computer and Communications Security (CCS)

DOI: 10.1145/3460120.3484781

Authors: Yuxin Wang, Zeyu Ding, Yingtai Xiao, Daniel Kifer, Danfeng Zhang

Institution: Pennsylvania State University

Language: English

Topic: Privacy-Preserving Technologies in Data

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funder: National Science Foundation

Awards: SaTC: CORE: Small: New Techniques for Optimizing Accuracy in Differential Privacy Applications, SaTC: CORE: Medium: Developing for Differential Privacy with Formal Methods and Counterexamples