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 OpenAlexaff
Hsueh‐Ti Derek Liu, Michael Tao, Chunliang Li, Derek Nowrouzezahrai, Alec Jacobson

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.

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)0.002
metaresearch head score (Gemma)0.007
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 score0.011

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.007
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.000
Science and technology studies0.0000.003
Scholarly communication0.0020.003
Open science0.0010.004
Research integrity0.0010.004
Insufficient payload (model declined to judge)0.0030.001

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 head0.108
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

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

Citations65
Published2018
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicAdversarial Robustness in Machine LearningFrench-language works237,207