MétaCan
Menu
Back to cohort

Towards Protecting Sensitive Text with Differential Privacy

2021· article· en· W4239403641 on OpenAlexaff
Sam Fletcher, Adam Roegiest, Alexander K. Hudek

Bibliographic record

Venue2021 IEEE 20th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · 2021
Typearticle
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsCisco Systems (Canada)Merck Canada Inc. (Canada)
Fundersnot available
KeywordsDifferential privacyComputer scienceFeature (linguistics)Hash functionData miningMasking (illustration)Table (database)Information retrievalTheoretical computer scienceArtificial intelligenceComputer security

Abstract

fetched live from OpenAlex

Natural language processing can often require handling privacy-sensitive text. To avoid revealing confidential information, data owners and practitioners can use differential privacy, which provides a mathematically guaranteeable definition of privacy preservation. In this work, we explore the possibility of applying differential privacy to feature hashing. Feature hashing is a common technique for handling out-of-dictionary vocabulary, and for creating a lookup table to find feature weights in constant time. Traditionally, differential privacy involves adding noise to hide the true value of data points. We show that due to the finite nature of the output space when using feature hashing, a noiseless approach is also theoretically sound. This approach opens up the possibility of applying strong differential privacy protections to NLP models trained with feature hashing. Preliminary experiments show that even common words can be protected with (0.04,10−5)-differential privacy, with only a minor reduction in model utility.

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)0.014
metaresearch head score (Gemma)0.064
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.014
Threshold uncertainty score0.074

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0140.064
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0020.003
Science and technology studies0.0020.007
Scholarly communication0.0060.021
Open science0.0040.012
Research integrity0.0030.007
Insufficient payload (model declined to judge)0.0040.003

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 head0.057
GPT teacher head0.323
Teacher spread0.266 · 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 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

Citations3
Published2021
Admission routes1
Has abstractyes

Explore more

Same venue2021 IEEE 20th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)Same topicPrivacy-Preserving Technologies in DataFrench-language works237,207