|
--- |
|
title: Prompt Injection Detection Benchmark |
|
emoji: 📝 |
|
colorFrom: yellow |
|
colorTo: gray |
|
sdk: gradio |
|
sdk_version: 5.6.0 |
|
pinned: true |
|
license: apache-2.0 |
|
--- |
|
|
|
Simple app to benchmark popular prompt injection detection APIs. |
|
|
|
## Requirements |
|
|
|
1. Clone the repo |
|
|
|
2. Install dependencies (preferably in a virtual environment) |
|
|
|
```sh |
|
pip install -r requirements.txt |
|
``` |
|
|
|
3. Start the app: |
|
|
|
```sh |
|
gradio app.py |
|
``` |
|
|
|
## Supported providers |
|
|
|
- HuggingFace models |
|
- [Lakera](https://lakera.ai/) |
|
- [Azure Content Safety AI](https://learn.microsoft.com/en-us/azure/ai-services/content-safety/studio-quickstart) |
|
- [AWS Bedrock Guardrails](https://aws.amazon.com/bedrock/guardrails/) (coming soon) |
|
- [SydeLabs](https://www.sydelabs.ai/) |
|
|
