walledai/AdvBench download history

walledai/AdvBench is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 14,275 times (2,584 in the last 7 days), and 171,791 times in total. It ranks #2,196 among datasets by monthly downloads.

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 setti

Models trained on AdvBench

9 models list it as training data.

Spaces using AdvBench

Open walledai/AdvBench on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.