MétaCan
Menu
Back to cohort
Record W7105933270 · doi:10.23952/jano.7.2025.3.02

Towards robust adversarial examples for deep neural networks

2025· article· en· W7105933270 on OpenAlexvenueno aff

Bibliographic record

VenueJournal of Applied and Numerical Optimization · 2025
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsnot available
Fundersnot available
KeywordsAdversarial systemArtificial neural networkDeep learningDeep neural networksKey (lock)Feature (linguistics)

Abstract

fetched live from OpenAlex

In this paper, we show two methods to compute sampling-robust adversarial examples (AEs) for deep neural networks with rectilinear units (DNNs).Both methods use an adjustable robust counterpart of a MILP model by Fischetti an Jo.They rely on new uncertainty sets in (pseudo-)metric spaces of DNNs with identical structure and compact inputs.One method (the inner method) needs full information on weights and biases of a nominal DNN after training.The other one (the outer method) only needs full information on the training data and the training method used.We compare the two methods in experiments on DNNs classifying small fashion images according to the type of apparel shown.While the inner method generates AEs that are only robust w.r.t.very mild retraining of a DNN, the outer method leads to AEs that are robust w.r.t.retraining from scratch on the same training data.The outer approach can therefore in principle be used for grey-box attacks of DNNs with no knowledge on internal parameters after training.

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.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.010
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
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 score0.003
Threshold uncertainty score0.016

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.010
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.000
Science and technology studies0.0000.002
Scholarly communication0.0010.002
Open science0.0020.004
Research integrity0.0020.003
Insufficient payload (model declined to judge)0.0020.001

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 head0.010
GPT teacher head0.244
Teacher spread0.234 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJournal of Applied and Numerical OptimizationSame topicAdversarial Robustness in Machine LearningFrench-language works237,207