MétaCan
Menu
Back to cohort
Record W3181970103 · doi:10.1109/cvprw53098.2021.00371

A Watermarking-Based Framework for Protecting Deep Image Classifiers Against Adversarial Attacks

2021· article· en· W3181970103 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.
fundA Canadian funder is recorded on the work.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsUniversity of Waterloo
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsDigital watermarkingAdversarial systemArtificial intelligenceComputer scienceWatermarkDeep learningEncoderImage (mathematics)Robustness (evolution)Classifier (UML)Pattern recognition (psychology)AdversaryContextual image classificationComputer visionComputer security

Abstract

fetched live from OpenAlex

Although deep learning-based models have achieved tremendous success in image-related tasks, they are known to be vulnerable to adversarial examples—inputs with imperceptible, but subtly crafted perturbation which fool the models to produce incorrect outputs. To distinguish adversarial examples from benign images, in this paper, we propose a novel watermarking-based framework for protecting deep image classifiers against adversarial attacks. The proposed framework consists of a watermark encoder, a possible adversary, and a detector followed by a deep image classifier to be protected. Specific methods of watermarking and detection are also presented. It is shown by experiment on a subset of ImageNet validation dataset that the proposed framework along with the presented methods of watermarking and detection is effective against a wide range of advanced attacks (static and adaptive), achieving a near zero (effective) false negative rate for FGSM and PGD attacks (static and adaptive) with the guaranteed zero false positive rate. In addition, for all tested deep image classifiers (ResNet50V2, MobileNetV2, InceptionV3), the impact of watermarking on classification accuracy is insignificant with, on average, 0.63% and 0.49% degradation in top 1 and top 5 accuracy, respectively.

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)0.003
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: Methods · Consensus signal: Methods
Teacher disagreement score0.579
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.003
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0010.000
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 head0.019
GPT teacher head0.292
Teacher spread0.273 · 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