MétaCan
Menu
Back to cohort
Record W2952911150 · doi:10.48550/arxiv.1808.02651

Beyond Pixel Norm-Balls: Parametric Adversaries using an Analytically\n Differentiable Renderer

2018· preprint· W2952911150 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

VenuearXiv (Cornell University) · 2018
Typepreprint
Language
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsMcGill UniversityUniversity of Toronto
Fundersnot available
KeywordsDifferentiable functionNorm (philosophy)Parametric statisticsComputer sciencePixelMathematicsPure mathematicsComputer visionPolitical scienceLaw

Abstract

fetched live from OpenAlex

Many machine learning image classifiers are vulnerable to adversarial\nattacks, inputs with perturbations designed to intentionally trigger\nmisclassification. Current adversarial methods directly alter pixel colors and\nevaluate against pixel norm-balls: pixel perturbations smaller than a specified\nmagnitude, according to a measurement norm. This evaluation, however, has\nlimited practical utility since perturbations in the pixel space do not\ncorrespond to underlying real-world phenomena of image formation that lead to\nthem and has no security motivation attached. Pixels in natural images are\nmeasurements of light that has interacted with the geometry of a physical\nscene. As such, we propose the direct perturbation of physical parameters that\nunderly image formation: lighting and geometry. As such, we propose a novel\nevaluation measure, parametric norm-balls, by directly perturbing physical\nparameters that underly image formation. One enabling contribution we present\nis a physically-based differentiable renderer that allows us to propagate pixel\ngradients to the parametric space of lighting and geometry. Our approach\nenables physically-based adversarial attacks, and our differentiable renderer\nleverages models from the interactive rendering literature to balance the\nperformance and accuracy trade-offs necessary for a memory-efficient and\nscalable adversarial data augmentation workflow.\n

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)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies, Scholarly communication, Open science, Research integrity, Insufficient payload (model declined to judge)
Consensus categoriesMeta-epidemiology (narrow), Open science, Research integrity
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 score0.610
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0020.006
Science and technology studies0.0020.002
Scholarly communication0.0010.004
Open science0.0080.010
Research integrity0.0020.003
Insufficient payload (model declined to judge)0.0010.000

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 head0.108
GPT teacher head0.233
Teacher spread0.125 · 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