MétaCan
Menu
Back to cohort
Record W7112209861

ROBUST MACHINE LEARNING USING SUPERQUANTILES

2021· dissertation· W7112209861 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.

aboutThe title or abstract carries a Canadian signal from the geographic lexicon.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueCalhoun: The Naval Postgraduate School Institutional Archive (Naval Postgraduate School) · 2021
Typedissertation
Language
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsnot available
Fundersnot available
KeywordsRobustness (evolution)Adversarial systemArtificial neural networkComputationSupport vector machineOnline machine learningDeep learningRobotics
DOInot available

Abstract

fetched live from OpenAlex

The proliferation of machine learning in image recognition and natural language processing applications comes with increasing risk of adversarial attacks. Such attacks can potentially spoof automated detection systems in our drones or defeat facial recognition systems and bypass automated security systems. Typical defense techniques involve long training times, which would not be viable in an operational setting. The thesis utilizes a novel superquantile-based formulation to train machine learning systems to make them more robust to noise and adversarial attacks, while incurring less training costs compared to typical adversarial training techniques. The concept is explored in the context of support vector machines and achieves similar results as in the case of L1-regularization models. Subsequently, the concept is developed for neural network training with robustness tests on commonly referenced Modified National Institute of Standards and Technology (MNIST) and Canadian Institute for Advanced Research–10 classes (CIFAR-10) datasets. The test results demonstrate robustness against random noise perturbations and benchmark against typical adversarial training shows comparable results. This initial excursion into superquantile training sets the foundation for further exploration into improving machine learning robustness within less computation time.

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)0.006
metaresearch head score (Gemma)0.015
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Meta-epidemiology (narrow), Science and technology studies, Scholarly communication, Open science, Research integrity, Insufficient payload (model declined to judge)
Consensus categoriesMeta-epidemiology (narrow), Science and technology studies, Research integrity, Insufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.318
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0060.015
Meta-epidemiology (narrow)0.0060.005
Meta-epidemiology (broad)0.0040.004
Bibliometrics0.0020.006
Science and technology studies0.0150.004
Scholarly communication0.0060.005
Open science0.0100.005
Research integrity0.0020.021
Insufficient payload (model declined to judge)0.0010.003

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 head0.054
GPT teacher head0.282
Teacher spread0.228 · 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