Construct · 1 fields · 1 citations

universal adversarial triggers: a standalone construct

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

● anchor · a standalone construct Nearest construct by meaning·not indexed
universaladversarial triggers1 CONSTRUCTUniversal adversarialWALLACE · NATURAL LANGUAGE

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

Natural language processing

short input-agnostic token sequences that, added to any input, push a language model toward a chosen prediction or output.

In natural language processing, universal adversarial triggers refers to short input-agnostic token sequences that, added to any input, push a language model toward a chosen prediction or output. This meaning comes from Wallace (2019) in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP).[1]

Unit
Recovery means
Measured by

Next

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

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

Open in ColliderExport BibTeXReport this entry

Nearby constructs

joint2 fields · 2 citationsjingle · one word, two constructsmodel3 fields · 3 citationsjingle · one word, three constructsnatural3 fields · 7 citationsjingle · one word, three constructs

References

  1. Wallace, E., Feng, S., Kandpal, N., Gardner, M., & Singh, S. (2019). Universal Adversarial Triggers for Attacking and Analyzing NLP. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). https://doi.org/10.18653/v1/d19-1221

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