3nesdeniz/guardrail-hard-negatives download history

3nesdeniz/guardrail-hard-negatives is a text classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 100 times (44 in the last 7 days), and 343 times in total. It ranks #113,901 among datasets by monthly downloads.

Guardrail Hard Negatives (EN/TR) A false-positive stress test for guardrails. A curated, paired benign/attack dataset for evaluating and training prompt-injection detectors and LLM guardrails. A bilingual false-positive challenge set: benign prompts that look like attacks (security re

Models trained on guardrail-hard-negatives

2 models list it as training data.

Open 3nesdeniz/guardrail-hard-negatives on Hugging Face

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