MétaCan
Menu
Back to cohort

A Customized Text Sanitization Mechanism with Differential Privacy

2023· article· en· W4385570555 on OpenAlexaff
Sai Chen, Fengran Mo, Yanhao Wang, Cen Chen, Jian‐Yun Nie, Chengyu Wang, Jamie Cui

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsUniversité de Montréal
FundersNational Natural Science Foundation of China
KeywordsComputer scienceDifferential privacySecurity tokenMetric (unit)Benchmark (surveying)Set (abstract data type)Similarity (geometry)Information privacyMechanism (biology)Measure (data warehouse)Data miningInformation retrievalTheoretical computer scienceArtificial intelligenceComputer securityProgramming language

Abstract

fetched live from OpenAlex

As privacy issues are receiving increasing attention within the Natural Language Processing (NLP) community, numerous methods have been proposed to sanitize texts subject to differential privacy.However, the state-of-theart text sanitization mechanisms based on metric local differential privacy (MLDP) do not apply to non-metric semantic similarity measures and cannot achieve good trade-offs between privacy and utility.To address the above limitations, we propose a novel Customized Text (CusText) sanitization mechanism based on the original ϵ-differential privacy (DP) definition, which is compatible with any similarity measure.Furthermore, CusText assigns each input token a customized output set of tokens to provide more advanced privacy protection at the token level.Extensive experiments on several benchmark datasets show that CusText achieves a better trade-off between privacy and utility than existing mechanisms.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.005
metaresearch head score (Gemma)0.021
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.005
Threshold uncertainty score0.028

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0050.021
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0020.003
Science and technology studies0.0020.003
Scholarly communication0.0030.009
Open science0.0040.008
Research integrity0.0020.003
Insufficient payload (model declined to judge)0.0050.002

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 head0.024
GPT teacher head0.252
Teacher spread0.229 · 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; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
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

Citations26
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicPrivacy-Preserving Technologies in DataFrench-language works237,207