## **PoC**
[promptintel](https://promptintel.novahunting.ai/) is an interactive website containing only Adversarial Prompts.
[The dataset](https://huggingface.co/datasets/deadbits/vigil-jailbreak-all-MiniLM-L6-v2) , [backup link](https://github.com/deadbits/vigil-llm)
[hackaprompt dataset](https://huggingface.co/datasets/hackaprompt/hackaprompt-dataset) contains 600K+ adversarial prompts against three popular LLMs (ChatGPT, GPT-3, and FLAN)
## **Details**
`Vigil` is a Python framework and REST API for assessing Large Language Model (LLM) prompts against a set of scanners to detect prompt injections, jailbreaks, and other potentially risky inputs.
[Paper](https://arxiv.org/abs/2308.01263)