Construct · 1 fields · 1 citations

randomized smoothing: 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

turning any classifier into one with certified robustness under an L2 norm bound by predicting the most likely class under Gaussian noise added to the input.

In machine learning security, randomized smoothing refers to turning any classifier into one with certified robustness under an L2 norm bound by predicting the most likely class under Gaussian noise added to the input. This meaning comes from Cohen (2019) in arXiv.[1]

Unit
Recovery means
Measured by

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

See how randomized smoothing 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

class3 fields · 3 citationsjingle · one word, three constructs learning6 fields · 14 citationsjingle · one name, six constructs noise4 fields · 5 citationsjingle · one word, four constructs

References

Cohen, J. M., Rosenfeld, E., & Kolter, J. Z. (2019). Certified Adversarial Robustness via Randomized Smoothing. arXiv. https://doi.org/10.48550/arxiv.1902.02918

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