MétaCan
Menu
Back to cohort
Record W4384663134 · doi:10.1109/tnnls.2023.3290592

Asymptotic Behavior of Adversarial Training in Binary Linear Classification

2023· article· en· W4384663134 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

VenueIEEE Transactions on Neural Networks and Learning Systems · 2023
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsUniversity of British Columbia
FundersKing Abdullah University of Science and TechnologyNational Science Foundation
KeywordsAdversarial systemTraining (meteorology)Binary classificationBinary numberArtificial intelligencePattern recognition (psychology)Training setComputer scienceMachine learningMathematicsGeographySupport vector machineArithmetic

Abstract

fetched live from OpenAlex

Adversarial training using empirical risk minimization (ERM) is the state-of-the-art method for defense against adversarial attacks, that is, against small additive adversarial perturbations applied to test data leading to misclassification. Despite being successful in practice, understanding the generalization properties of adversarial training in classification remains widely open. In this article, we take the first step in this direction by precisely characterizing the robustness of adversarial training in binary linear classification. Specifically, we consider the high-dimensional regime where the model dimension grows with the size of the training set at a constant ratio. Our results provide exact asymptotics for both standard and adversarial test errors under general -norm bounded perturbations ( ) in both discriminative binary models and generative Gaussian-mixture models with correlated features. We use our sharp error formulae to explain how the adversarial and standard errors depend upon the over-parameterization ratio, the data model, and the attack budget. Finally, by comparing with the robust Bayes estimator, our sharp asymptotics allow us to study the fundamental limits of adversarial 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.

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 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 score0.730
Threshold uncertainty score0.749

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 science0.0000.000
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 head0.035
GPT teacher head0.276
Teacher spread0.241 · 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