Constarium
← Search

Table · dataset · 2024

walledai/AdvBench

Listed in Hugging Face Datasets

Description

Dataset Card for AdvBench Paper: Universal and Transferable Adversarial Attacks on Aligned Language Models Data: AdvBench Dataset About AdvBench is a set of 500 harmful behaviors formulated as instructions. These behaviors range over the same themes as the harmful strings setting, but the adversary’s goal is instead to find a single attack string that will cause the model to generate any response that attempts to comply with the instruction, and to do so over as many… See the full description on the dataset page: huggingface.co/datasets/walledai/AdvBench.

Links

Get the data

Documentation and papers

Catalogue records · 1

Topics

Stated by source
text
Inferred from text
Machine learning 70%
Provenance · 1 source records, 10 field assertions
SourceKeyLast seenRaw
Hugging Face Datasetswalledai/AdvBench12 d agoJSON v1
FieldAssertionExtractorEvidence
access_levelsource · Hugging Faceconnector:huggingface@1.0.0/gated
concepts[field].anzsrc:group:4611enrichment · Hugging Facetaxonomy-embedding@1.1.0title+keywords+description (70%)
concepts[field].local:field:computer-science-aimapping · Hugging Faceconnector:huggingface@1.0.0
concepts[modality].hf_modality:textsource · Hugging Faceconnector:huggingface@1.0.0
created_datesource · Hugging Faceconnector:huggingface@1.0.0
descriptionsource · Hugging Faceconnector:huggingface@1.0.0/description
licensesource · Hugging Faceconnector:huggingface@1.0.0/tags[license:*]
publication_datesource · Hugging Faceconnector:huggingface@1.0.0
titlesource · Hugging Faceconnector:huggingface@1.0.0/id
updated_datesource · Hugging Faceconnector:huggingface@1.0.0