Construct · 1 fields · 1 citations

universal adversarial perturbation: a standalone construct

One name. One construct. A landmark on the map.

● anchor · a standalone construct Nearest construct by meaning·not indexed

A single standalone construct; nearby constructs are located against it in the Collider. Tap a field for its definition, unit, and measures.

Machine learning security

a single small image-agnostic perturbation that causes a classifier to mislabel most natural images it is added to.

In machine learning security, universal adversarial perturbation refers to a single small image-agnostic perturbation that causes a classifier to mislabel most natural images it is added to. This meaning comes from Moosavi-Dezfooli (2016) in arXiv.[1]

Unit
Recovery means
Measured by

Run it through the Collider, or take the citations with you.

See how universal adversarial perturbation sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in Collider Export BibTeX Report this entry

Nearby constructs

adversarial example1 fields · 1 citationsanchor · a standalone construct learning6 fields · 14 citationsjingle · one name, six constructs natural3 fields · 7 citationsjingle · one word, three constructs

References

Moosavi-Dezfooli, S., Fawzi, A., Fawzi, O., & Frossard, P. (2016). Universal adversarial perturbations. arXiv. https://doi.org/10.48550/arxiv.1610.08401

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct