MétaCan
Menu
Back to cohort
Record W6979263332

Pr$εε$mpt: Sanitizing Sensitive Prompts for LLMs

2025· article· en· W6979263332 on OpenAlexfundno aff

Bibliographic record

VenueArXiv.org · 2025
Typearticle
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsnot available
FundersOffice of Naval ResearchNatural Sciences and Engineering Research Council of CanadaDefense Advanced Research Projects AgencyNational Science FoundationGovernment of CanadaCanadian Institute for Advanced Research
KeywordsEncryptionMetric (unit)Credit cardInformation sensitivityInferencePrivacy protection
DOInot available

Abstract

fetched live from OpenAlex

The rise of large language models (LLMs) has introduced new privacy challenges, particularly during inference where sensitive information in prompts may be exposed to proprietary LLM APIs. In this paper, we address the problem of formally protecting the sensitive information contained in a prompt while maintaining response quality. To this end, first, we introduce a cryptographically inspired notion of a prompt sanitizer which transforms an input prompt to protect its sensitive tokens. Second, we propose Pr$εε$mpt, a novel system that implements a prompt sanitizer. Pr$εε$mpt categorizes sensitive tokens into two types: (1) those where the LLM's response depends solely on the format (such as SSNs, credit card numbers), for which we use format-preserving encryption (FPE); and (2) those where the response depends on specific values, (such as age, salary) for which we apply metric differential privacy (mDP). Our evaluation demonstrates that Pr$εε$mpt is a practical method to achieve meaningful privacy guarantees, while maintaining high utility compared to unsanitized prompts, and outperforming prior methods

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)0.012
metaresearch head score (Gemma)0.051
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 score0.012
Threshold uncertainty score0.063

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0120.051
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0010.001
Science and technology studies0.0010.003
Scholarly communication0.0040.011
Open science0.0030.009
Research integrity0.0020.006
Insufficient payload (model declined to judge)0.0070.003

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 head0.053
GPT teacher head0.303
Teacher spread0.250 · 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

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueArXiv.orgSame topicPrivacy-Preserving Technologies in DataFrench-language works237,207