Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security 2021
DOI: 10.1145/3460120.3484781
|View full text |Cite
|
Sign up to set email alerts
|

DPGen: Automated Program Synthesis for Differential Privacy

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 (nonprivate) 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 (with… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
3

Relationship

0
9

Authors

Journals

citations
Cited by 10 publications
(4 citation statements)
references
References 44 publications
0
4
0
Order By: Relevance
“…Dropout [43] and differential privacy [12], [1] are two widely used techniques in the fields of formal verification [48], program synthesis [49] and deep learning privacy protection [51], [46], [56]. Here we investigate the attack accuracy and model utility when they are adopted in FL that is under the attack of PPA.…”
Section: B Defensesmentioning
confidence: 99%
“…Dropout [43] and differential privacy [12], [1] are two widely used techniques in the fields of formal verification [48], program synthesis [49] and deep learning privacy protection [51], [46], [56]. Here we investigate the attack accuracy and model utility when they are adopted in FL that is under the attack of PPA.…”
Section: B Defensesmentioning
confidence: 99%
“…Dropout [41] and differential privacy [12] are two widely used techniques in the fields of formal verification [45], program synthesis [46] and deep learning privacy protection [44,48,53]. Here we investigate the attack accuracy and model utility when PPA is adopted in FL.…”
Section: When Our Attack Confronts Defensesmentioning
confidence: 99%
“…Later approaches [6,35,36,38,40] rely on the SMT solver Z3 [12], the MaxSMT solver νZ [8], or the probabilistic analysis tool PSI [24] to minimize the manual effort necessary to prove or disprove differential privacy. Wang et al's tool DPGen [37] can even transform programs violating differential privacy into differentially private ones. Recent work by Bichsel et al [7] uses machine learning to detect differential privacy violations.…”
Section: Related Workmentioning
confidence: 99%