jackhhao/jailbreak-classification download history
jackhhao/jailbreak-classification is a text classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 5,449 times (1,818 in the last 7 days), and 57,327 times in total. It ranks #5,317 among datasets by monthly downloads.
Jailbreak Classification Dataset Summary Dataset used to classify prompts as jailbreak vs. benign. Dataset Structure Data Fields prompt: an LLM prompt type: classification label, either jailbreak or benign Dataset Creation Curation Rat
Models trained on jailbreak-classification
30 models list it as training data.
- protectai/deberta-v3-base-prompt-injection-v2 763.8K downloads in 30 days
- codeintegrity-ai/promptguard 19.6K downloads in 30 days
- protectai/deberta-v3-small-prompt-injection-v2 2.8K downloads in 30 days
- jackhhao/jailbreak-classifier 1.7K downloads in 30 days
- dannyliv/agent-guard-modernbert-base 527 downloads in 30 days
- RedHatAI/deberta-v3-base-prompt-injection-v2 133 downloads in 30 days
- vllm-sr/Decision-1.0-Route-0.6B 63 downloads in 30 days
- anon767tom/smolaya 45 downloads in 30 days
- centiv-ai-admin/deberta-v3-base-prompt-injection-v2 39 downloads in 30 days
- opus-research/opus-moderation-2 37 downloads in 30 days
- dannyliv/agent-guard-deberta-pi-base 35 downloads in 30 days
- samratduttaofficial/WaterSheep 33 downloads in 30 days
Open jackhhao/jailbreak-classification on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.