Construct · 1 fields · 1 citations

projected gradient descent attack: 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

an iterative attack that takes repeated gradient steps to raise a model's loss and projects back into an allowed perturbation ball, framed as a robust optimization problem.

In machine learning security, projected gradient descent attack refers to an iterative attack that takes repeated gradient steps to raise a model's loss and projects back into an allowed perturbation ball, framed as a robust optimization problem. This meaning comes from Madry (2017) in arXiv.[1]

Unit
Recovery means
Measured by

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

See how projected gradient descent attack 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

attack4 fields · 10 citationsjingle · one word, four constructs descent3 fields · 4 citationsjingle · one word, three constructs gradient descent1 fields · 4 citationsanchor · a standalone construct

References

Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2017). Towards Deep Learning Models Resistant to Adversarial Attacks. arXiv. https://doi.org/10.48550/arxiv.1706.06083

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