MétaCan
Menu
Back to cohort
Record W4406309654 · doi:10.62056/ahmpdkp10

Publicly-Detectable Watermarking for Language Models

2025· article· en· W4406309654 on OpenAlexaff
Jaiden Fairoze, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, M. Wang

Bibliographic record

VenueIACR Communications in Cryptology · 2025
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Steganography and Watermarking Techniques
Canadian institutionsArtificial Intelligence in Medicine (Canada)
FundersArmy Research OfficeAir Force Office of Scientific ResearchNational Science Foundation
KeywordsDigital watermarkingComputer scienceComputer securityArtificial intelligence

Abstract

fetched live from OpenAlex

We present a publicly-detectable watermarking scheme for LMs: the detection algorithm contains no secret information, and it is executable by anyone. We embed a publicly-verifiable cryptographic signature into LM output using rejection sampling and prove that this produces unforgeable and distortion-free (i.e., undetectable without access to the public key) text output. We make use of error-correction to overcome periods of low entropy, a barrier for all prior watermarking schemes. We implement our scheme and find that our formal claims are met in practice.

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)0.003
metaresearch head score (Gemma)0.023
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: Methods · Consensus signal: Methods
Teacher disagreement score0.006
Threshold uncertainty score0.019

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.023
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0010.001
Science and technology studies0.0010.004
Scholarly communication0.0040.011
Open science0.0020.005
Research integrity0.0020.004
Insufficient payload (model declined to judge)0.0060.002

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 head0.037
GPT teacher head0.341
Teacher spread0.304 · 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
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

Citations10
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueIACR Communications in CryptologySame topicAdvanced Steganography and Watermarking TechniquesFrench-language works237,207