MétaCan
Menu
Back to cohort

Can’t Hide Behind the API: Stealing Black-Box Commercial Embedding Models

2025· article· en· W4411112895 on OpenAlexafffund
Manveer Singh Tamber, Jasper Xian, Jimmy Lin

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldDecision Sciences
TopicData Quality and Management
Canadian institutionsUniversity of Waterloo
FundersNatural Sciences and Engineering Research Council of CanadaCompute Canada
KeywordsComputer scienceEmbeddingBlack boxComputer securityArtificial intelligence

Abstract

fetched live from OpenAlex

Embedding models that generate dense vector representations of text are widely used and hold significant commercial value.Companies such as OpenAI and Cohere offer proprietary embedding models via paid APIs, but despite being "hidden" behind APIs, these models are not protected from theft.We present, to our knowledge, the first effort to "steal" these models for retrieval by training thief models on text-embedding pairs obtained from the APIs.Our experiments demonstrate that it is possible to replicate the retrieval effectiveness of commercial embedding models with a cost of under $300.Notably, our methods allow for distilling from multiple teachers into a single robust student model, and for distilling into presumably smaller models with fewer dimension vectors, yet competitive retrieval effectiveness.Our findings raise important considerations for deploying commercial embedding models and suggest measures to mitigate the risk of model theft.

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)0.005
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.905
Threshold uncertainty score0.653

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0050.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.000
Open science0.0020.001
Research integrity0.0000.000
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 head0.214
GPT teacher head0.451
Teacher spread0.237 · 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.

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

Citations2
Published2025
Admission routes2
Has abstractyes

Explore more

Same topicData Quality and ManagementFrench-language works237,207