DatasetRank #633 of 836 123 likes

AdvBench

Name: AdvBench
Creator: walledai
License: https://spdx.org/licenses/MIT.html

by walledai (organization)

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… (excerpt from the dataset card on Hugging Face)

Access requires accepting terms on Hugging Face.

View on Hugging Face

Dataset facts

Hub id: walledai/AdvBench
Likes: 123
Downloads (last 30 days): 11,118
Tasks: Not given
Modality: text
Size: Fewer than 1K examples
License: MIT (mit)
Access: Gated: access is granted on accepting the terms
Author: walledai · Organization
Languages: en
Created: Jul 2, 2024
Last modified: Jul 4, 2024

Rank #633 of 836 datasets in AI on Hugging Face, by likes. Data from the Hugging Face Hub API, fetched Oct 18, 2026. Likes measure popularity, not quality or safety. Downloads are for the last 30 days, as the Hub reports them; counts change daily. A listing is not an endorsement. How this list is made

Dataset facts

Support Us