SoK: Differential Privacies

Desfontaines, Damien; Pejó, Balázs

doi:10.48550/arxiv.1906.01337

Cited by 10 publications

(13 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DP was first introduced by Dwork et al (2006b) which defined the concept of anindistinguishable RM, now commonly known as -DP or "pure" DP RM. Since then, DP as a framework has spawned a massive number of new privacy definitions (Desfontaines & Pejó 2019). Because of this, it is often unclear and debated what makes any particular property emblematic of "DP."…”

Section: General Setupmentioning

confidence: 99%

Statistical Data Privacy: A Song of Privacy and Utility

Slavković¹,

Seeman²

2022

Preprint

View full text Add to dashboard Cite

To quantify trade-offs between increasing demand for open data sharing and concerns about sensitive information disclosure, statistical data privacy (SDP) methodology analyzes data release mechanisms which sanitize outputs based on confidential data. Two dominant frameworks exist: statistical disclosure control (SDC), and more recent, differential privacy (DP). Despite framing differences, both SDC and DP share the same statistical problems at its core. For inference problems, we may either design optimal release mechanisms and associated estimators that satisfy bounds on disclosure risk, or we may adjust existing sanitized output to create new optimal estimators. Both problems rely on uncertainty quantification in evaluating risk and utility. In this review, we discuss the statistical foundations common to both SDC and DP, highlight major developments in SDP, and present exciting open research problems in private inference.

show abstract

Section: General Setupmentioning

confidence: 99%

Statistical Data Privacy: A Song of Privacy and Utility

Slavković¹,

Seeman²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In this paper, we use the zero-Concentrated Differential Privacy (zCDP, see Definition 3.4) as the privacy measurement, because it provides the simplicity and possibility of adaptively composing privacy costs at each iteration. Various privacy metrics are discussed or reviewed in (Desfontaines & Pejó, 2019). A notable example is Moment Accoutant (MA) (Abadi et al, 2016), which adopts similar principle for composing privacy costs while is less tight for a smaller privacy budget.…”

Section: Assumptionsmentioning

confidence: 99%

Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent

Hong¹,

Wang²,

Zhou³

2021

Preprint

View full text Add to dashboard Cite

Protecting privacy in learning while maintaining the model performance has become increasingly critical in many applications that involve sensitive data. Private Gradient Descent (PGD) is a commonly used private learning framework, which noises gradients based on the Differential Privacy protocol. Recent studies show that dynamic privacy schedules of decreasing noise magnitudes can improve loss at the final iteration, and yet theoretical understandings of the effectiveness of such schedules and their connections to optimization algorithms remain limited. In this paper, we provide comprehensive analysis of noise influence in dynamic privacy schedules to answer these critical questions. We first present a dynamic noise schedule minimizing the utility upper bound of PGD, and show how the noise influence from each optimization step collectively impacts utility of the final model. Our study also reveals how impacts from dynamic noise influence change when momentum is used. We empirically show the connection exists for general non-convex losses, and the influence is greatly impacted by the loss curvature.

show abstract

“…A significant amount of research focuses on improving the accuracy of query results while still maintaining differential privacy. In this work, for clarity, we keep the description of our system conceptually simple, and explicitly do not make use of techniques like smooth sensitivity [40], tight privacy budget computation methods [22,35], variants of the differential privacy definition [6,8,37], adjustment of noise levels to a prespecified set of queries [30], or generation of differentially private synthetic data to answer arbitrarily many queries afterwards [5,26,27].…”

Section: Related Workmentioning

confidence: 99%

Differentially Private SQL with Bounded User Contribution

Wilson¹,

Zhang²,

Lam³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Differential privacy (DP) provides formal guarantees that the output of a database query does not reveal too much information about any individual present in the database. While many differentially private algorithms have been proposed in the scientific literature, there are only a few end-to-end implementations of differentially private query engines. Crucially, existing systems assume that each individual is associated with at most one database record, which is unrealistic in practice. We propose a generic and scalable method to perform differentially private aggregations on databases, even when individuals can each be associated with arbitrarily many rows. We express this method as an operator in relational algebra, and implement it in an SQL engine. To validate this system, we test the utility of typical queries on industry benchmarks, and verify its correctness with a stochastic test framework we developed. We highlight the promises and pitfalls learned when deploying such a system in practice, and we publish its core components as open-source software.

show abstract

SoK: Differential Privacies

Cited by 10 publications

References 0 publications

Statistical Data Privacy: A Song of Privacy and Utility

Statistical Data Privacy: A Song of Privacy and Utility

Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent

Differentially Private SQL with Bounded User Contribution

Contact Info

Product

Resources

About