rogue-security/prompt-injections-benchmark download history

rogue-security/prompt-injections-benchmark is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 3,048 times (2,465 in the last 7 days), and 21,343 times in total. It ranks #11,949 among datasets by monthly downloads.

Dataset: Qualifire Benchmark Prompt Injection(Jailbreak vs. Benign) Datasets Overview This dataset contains 5,000 prompts, each labeled as either jailbreak or benign. The dataset is designed for evaluating AI models' robustness against adversarial prompts and their abil

Models trained on prompt-injections-benchmark

4 models list it as training data.

Downloads by month

Downloads in the 30 days up to the end of each month, and the change from the month before.

MonthDownloadsChange
Up to 2026-11-183,048+275%
October 2026812-29%
September 20261,144+27%
August 2026898-11%
July 20261,012-20%
June 20261,271+40%
May 2026910-9%
April 2026998-10%
March 20261,109-8%
February 20261,203+61%
January 2026746-16%
December 2025892-46%

Its busiest 30 days so far ended on 2026-11-18, with 3,048 downloads.

Open rogue-security/prompt-injections-benchmark on Hugging Face

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