Prompt-injection-dataset

Summary

A high-quality, leakage-free binary classification dataset for detecting **prompt injection** and **jailbreak** attacks against Large Language Models.

Keywords

hf-dataset parquet optimized-parquet text datasets pandas polars mlcroissant prompt-injection jailbreak security llm-security prompt-security cybersecurity attack-detection ai-safety

Research notes

• downloads=2318; likes=24