S-Labs/prompt-injection-dataset download history
S-Labs/prompt-injection-dataset is a text classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,042 times (376 in the last 7 days), and 4,315 times in total. It ranks #18,745 among datasets by monthly downloads.
Prompt Injection Detection Dataset A binary classification dataset for detecting prompt injection attacks in user inputs to LLM-based applications. Dataset Description This dataset is designed to train encoder-only models (e.g., BERT, RoBERTa, DistilBERT) to classify user input
Models trained on prompt-injection-dataset
5 models list it as training data.
- Horizon-Labs/prompt-injection-guard-base 757 downloads in 30 days
- Horizon-Labs/prompt-injection-guard-small 491 downloads in 30 days
- Horizon-Labs/prompt-injection-guard-large 73 downloads in 30 days
- AWuhrmann/tripwire-prompt-injection-base 42 downloads in 30 days
- sdmlai/cyber-jev 17 downloads in 30 days