MétaCan
Menu
Back to cohort
Record W4225853051 · doi:10.5281/zenodo.6368376

DP-VAE: Human-Readable Text Anonymization for Online Reviews with Differentially Private Variational Autoencoders

2022· article· en· W4225853051 on OpenAlexaff
Benjamin Weggenmann, Valentin Rublack, Michael Andrejczuk, Justus Mattern, Florian Kerschbaum

Bibliographic record

VenueZenodo (CERN European Organization for Nuclear Research) · 2022
Typearticle
Languageen
FieldComputer Science
TopicAuthorship Attribution and Profiling
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsComputer scienceArtificial intelligencePrivate information retrievalData scienceInformation retrievalComputer security

Abstract

fetched live from OpenAlex

While vast amounts of personal data are shared daily on public online platforms and used by companies and analysts to gain valuable insights, privacy concerns are also on the rise: Modern authorship attribution techniques have proven effective at identifying individuals from their data, such as their writing style or behavior of picking and judging movies. It is hence crucial to develop data sanitization methods that allow sharing of users' data while protecting their privacy and preserving quality and content of the original data. In this paper, we tackle anonymization of textual data and propose an end-to-end differentially private variational autoencoder architecture. Unlike previous approaches that achieve differential privacy on a per-word level through individual perturbations, our solution works at an abstract level by perturbing the latent vectors that provide a global summary of the input texts. Decoding an obfuscated latent vector thus not only allows our model to produce coherent, high-quality output text that is human-readable, but also results in strong anonymization due to the diversity of the produced data.<br> We evaluate our approach on IMDb movie and Yelp business reviews, confirming its anonymization capabilities and preservation of the semantics and utility of the original sentences.

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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesScience and technology studies, Insufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.816
Threshold uncertainty score0.997

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0040.000
Scholarly communication0.0010.000
Open science0.0010.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0050.000

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 head0.065
GPT teacher head0.279
Teacher spread0.215 · 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 teacher head, not a consensus.

Study designNot applicable
Domainnot available
GenreMethods

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

Citations0
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueZenodo (CERN European Organization for Nuclear Research)Same topicAuthorship Attribution and ProfilingFrench-language works237,207