Aquileo | GitHub - koswadi/prompt-injection-detection-dataset: A structured NLP dataset for detecting prompt injection attacks, jailbreak attempts, and malicious instruction manipulation in Large Language Models (LLMs). Includes annotated threat categories, risk classifications, and validation-ready samples for AI safety training, security evaluation, and adversarial robustness research.

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 1 Commit
data		data
docs		docs
examples		examples
images		images
LICENSE		LICENSE
README.md		README.md
dataset_card.md		dataset_card.md

Repository files navigation

About

A structured NLP dataset for detecting prompt injection attacks, jailbreak attempts, and malicious instruction manipulation in Large Language Models (LLMs). Includes annotated threat categories, risk classifications, and validation-ready samples for AI safety training, security evaluation, and adversarial robustness research.