MétaCan
Menu
Back to cohort
Record W2788235277 · doi:10.1109/smc.2019.8913861

Generalizable Adversarial Examples Detection Based on Bi-model Decision Mismatch

2019· preprint· en· W2788235277 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
Typepreprint
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsInstitut National de la Recherche Scientifique
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsAdversarial systemComputer scienceMNIST databaseMachine learningArtificial intelligenceDeep neural networksArtificial neural networkSet (abstract data type)Focus (optics)Binary classificationAdversarial machine learningDeep learning

Abstract

fetched live from OpenAlex

Modern applications of artificial neural networks have yielded remarkable performance gains in a wide range of tasks. However, recent studies have discovered that such modelling strategy is vulnerable to Adversarial Examples, i.e. examples with subtle perturbations often too small and imperceptible to humans, but that can easily fool neural networks. Defense techniques against adversarial examples have been proposed, but ensuring robust performance against varying or novel types of attacks remains an open problem. In this work, we focus on the detection setting, in which case attackers become identifiable while models remain vulnerable. Particularly, we employ the decision layer of independently trained models as features for posterior detection. The proposed framework does not require any prior knowledge of adversarial examples generation techniques, and can be directly employed along with unmodified off-the-shelf models. Experiments on the standard MNIST and CIFAR10 datasets deliver empirical evidence that such detection approach generalizes well across not only different adversarial examples generation methods but also quality degradation attacks. Non-linear binary classifiers trained on top of our proposed features can achieve a high detection rate (>90%) in a set of white-box attacks and maintain such performance when tested against unseen attacks.

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: Methods · Consensus signal: Methods
Teacher disagreement score0.442
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0010.000
Open science0.0030.002
Research integrity0.0010.001
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 head0.026
GPT teacher head0.276
Teacher spread0.249 · 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