MétaCan
Menu
Back to cohort
Record W2995459148 · doi:10.4230/lipics.itc.2020.14

The Power of Synergy in Differential Privacy: Combining a Small Curator with Local Randomizers

2019· preprint· en· W2995459148 on OpenAlexfundno aff
Amos Beimel, Aleksandra Korolova, Kobbi Nissim, Or Sheffet, Uri Stemmer

Bibliographic record

VenuearXiv (Cornell University) · 2019
Typepreprint
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsnot available
FundersSimons Institute for the Theory of Computing, University of California BerkeleyIsrael Science FoundationBen-Gurion University of the NegevNational Science FoundationVMwareNatural Sciences and Engineering Research Council of CanadaGeorgetown UniversityUniversity of Alberta
KeywordsDifferential privacyComputer scienceTask (project management)Protocol (science)Focus (optics)Differential (mechanical device)Simple (philosophy)Range (aeronautics)Power (physics)Bridge (graph theory)Human–computer interactionData miningEngineering

Abstract

fetched live from OpenAlex

Motivated by the desire to bridge the utility gap between local and trusted curator models of differential privacy for practical applications, we initiate the theoretical study of a hybrid model introduced by "Blender" [Avent et al., USENIX Security '17], in which differentially private protocols of n agents that work in the local-model are assisted by a differentially private curator that has access to the data of m additional users. We focus on the regime where m ≪ n and study the new capabilities of this (m,n)-hybrid model. We show that, despite the fact that the hybrid model adds no significant new capabilities for the basic task of simple hypothesis-testing, there are many other tasks (under a wide range of parameters) that can be solved in the hybrid model yet cannot be solved either by the curator or by the local-users separately. Moreover, we exhibit additional tasks where at least one round of interaction between the curator and the local-users is necessary - namely, no hybrid model protocol without such interaction can solve these tasks. Taken together, our results show that the combination of the local model with a small curator can become part of a promising toolkit for designing and implementing differential privacy.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.002
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Open science
Consensus categoriesOpen science
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.565
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.002
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.001
Science and technology studies0.0000.001
Scholarly communication0.0000.000
Open science0.0310.102
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.040
GPT teacher head0.187
Teacher spread0.147 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; both teacher heads agree on what is shown here.

Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations5
Published2019
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicPrivacy-Preserving Technologies in DataFrench-language works237,207