MétaCan
Menu
Back to cohort
Record W4288322434 · doi:10.48550/arxiv.1906.07745

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

2019· preprint· en· W4288322434 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

VenuearXiv (Cornell University) · 2019
Typepreprint
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsBackdoorDigital watermarkingWatermarkRobustness (evolution)Computer scienceDeep learningBlack boxArtificial neural networkArtificial intelligenceDeep neural networksSet (abstract data type)White boxComputer securityData miningMachine learningEmbeddingImage (mathematics)

Abstract

fetched live from OpenAlex

Obtaining the state of the art performance of deep learning models imposes a\nhigh cost to model generators, due to the tedious data preparation and the\nsubstantial processing requirements. To protect the model from unauthorized\nre-distribution, watermarking approaches have been introduced in the past\ncouple of years. We investigate the robustness and reliability of\nstate-of-the-art deep neural network watermarking schemes. We focus on\nbackdoor-based watermarking and propose two -- a black-box and a white-box --\nattacks that remove the watermark. Our black-box attack steals the model and\nremoves the watermark with minimum requirements; it just relies on public\nunlabeled data and a black-box access to the classification label. It does not\nneed classification confidences or access to the model's sensitive information\nsuch as the training data set, the trigger set or the model parameters. The\nwhite-box attack, proposes an efficient watermark removal when the parameters\nof the marked model are available; our white-box attack does not require access\nto the labeled data or the trigger set and improves the runtime of the\nblack-box attack up to seventeen times. We as well prove the security\ninadequacy of the backdoor-based watermarking in keeping the watermark\nundetectable by proposing an attack that detects whether a model contains a\nwatermark. Our attacks show that a recipient of a marked model can remove a\nbackdoor-based watermark with significantly less effort than training a new\nmodel and some other techniques are needed to protect against re-distribution\nby a motivated attacker.\n

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 score0.733
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0050.003
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 head0.041
GPT teacher head0.183
Teacher spread0.142 · 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