MétaCan
Menu
Back to cohort
Record W2952348804 · doi:10.1145/3437880.3460401

On the Robustness of Backdoor-based Watermarking in Deep Neural Networks

2021· preprint· en· W2952348804 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

Venuenot available
Typepreprint
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsBackdoorDigital watermarkingWatermarkRobustness (evolution)Computer scienceDeep learningBlack boxArtificial neural networkArtificial intelligenceWhite boxDeep neural networksSet (abstract data type)Computer securityData miningMachine learningEmbeddingImage (mathematics)

Abstract

fetched live from OpenAlex

Watermarking algorithms have been introduced in the past years to protect deep learning models against unauthorized re-distribution. We investigate the robustness and reliability of state-of-the-art deep neural network watermarking schemes. We focus on backdoor-based watermarking and propose two simple yet effective attacks -- a black-box and a white-box -- that remove these watermarks without any labeled data from the ground truth. Our black-box attack steals the model and removes the watermark with only API access to the labels. Our white-box attack proposes an efficient watermark removal when the parameters of the marked model are accessible, and improves the time to steal a model up to twenty times over the time to train a model from scratch. We conclude that these watermarking algorithms are insufficient to defend against redistribution by a motivated attacker.

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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.890
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0030.003
Research integrity0.0000.002
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 head0.018
GPT teacher head0.250
Teacher spread0.231 · 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