MétaCan
Menu
Back to cohort
Record W4417064600 · doi:10.1145/3773028

Securing Large Language Models: A Survey of Watermarking and Fingerprinting Techniques

2025· review· en· W4417064600 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueACM Computing Surveys · 2025
Typereview
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsArtificial Intelligence in Medicine (Canada)
FundersNational Natural Science Foundation of China
KeywordsDigital watermarkingFingerprint (computing)Intellectual propertySophisticationIngenuityAdversarial systemDigital Watermarking AllianceSecurity token

Abstract

fetched live from OpenAlex

State-of-the-art watermarking and fingerprinting techniques for Large Language Models (LLMs) are explored, with our analysis spanning a wide array of methodologies designed to protect the intellectual property of LLMs. The review of watermarking techniques is based on embedding watermarks during the training, logits generation, and token sampling phases. Meanwhile, we investigate the application of watermarking technology in multimodal LLMs and potential attacks on watermarks. Moreover, our examination of fingerprinting techniques revealed the ingenuity behind methods used to identify LLMs. We discussed the development of fingerprints based on model behavior and using deep learning models to learn thresholds for fingerprint comparison. Our survey has underscored the importance of advancing security measures for LLMs, especially in light of the increasing sophistication of adversarial attacks. As LLMs continue to play a pivotal role in advancing AI technologies, developing and refining security measures that safeguard their intellectual property and ensure their ethical deployment is imperative.

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.

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)0.015
metaresearch head score (Gemma)0.004
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Open science
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Review · Consensus signal: none
Teacher disagreement score0.983
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0150.004
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0030.008
Research integrity0.0000.001
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 head0.043
GPT teacher head0.348
Teacher spread0.305 · 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