Metadata-Version: 2.1
Name: zenguard-benchmarks
Version: 0.1.2
Summary: Test ZenGuard AI against different datasets and benchmarks.
License: MIT
Author: Baur Krykpayev
Author-email: baur@zenguard.ai
Requires-Python: >=3.9,<4.0
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Dist: datasets (>=3.0.1,<4.0.0)
Requires-Dist: httpx (>=0.27.2,<0.28.0)
Requires-Dist: matplotlib (>=3.9.2,<4.0.0)
Requires-Dist: pandas (>=2.2.3,<3.0.0)
Requires-Dist: tqdm (>=4.66.5,<5.0.0)
Description-Content-Type: text/markdown

<a href="https://docs.zenguard.ai/" target="_blank"><img src="https://img.shields.io/badge/docs-view-green" alt="Documentation"></a> [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT) [![PyPI version](https://img.shields.io/pypi/v/zenguard-benchmarks)](https://pypi.org/project/zenguard-benchmarks/) <a target="_blank" href="https://colab.research.google.com/github/ZenGuard-AI/zenguard-benchmarks/blob/main/assets/colabs/zenguard-benchmarks.ipynb">
  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>

# ZenGuard AI Benchmarks

This repository contains benchmarks for [ZenGuard AI](https://zenguard.ai) and information on how to run them.

There are two types of benchmarks that we run against ZenGuard AI:

1. Hugging Face datasets based benchmarks
2. ZenGuard AI Generated Benchmark - Zen Bench

Here you can find both benchmark results and how to run them yourself.

## Public Datasets benchmarks

We are constantly monitoring Hugging Face for new datasets that relate to GenAI security. Then we run them against ZenGuard AI to find any potential security issues with our product.

### ZenGuard AI Accuracy against Hugging Face datasets

| # | Dataset | Accuracy | Date Added |
|---|---------|----------|------------|

| 1 | [xTRam1/safe-guard-prompt-injection](https://huggingface.co/datasets/xTRam1/safe-guard-prompt-injection) | 96% | 2024-07-01 |
| 2 | [deepset/prompt-injections](https://huggingface.co/datasets/deepset/prompt-injections) | 87% | 2024-05-15 |
| 3 | [JasperLS/prompt-injections](https://huggingface.co/datasets/JasperLS/prompt-injections) | 87% | 2024-05-15 |
| 4 | [aporia-ai/prompt_injection](https://huggingface.co/datasets/aporia-ai/prompt_injection) | 87.68% | 2024-05-15 |

### Check for yourself. Or run your own dataset.

We have developed the [ZenGuard Benchmarks PyPi package](https://pypi.org/project/zenguard-benchmarks/) to help test and benchmark ZenGuard AI better.

Here are the instructions on how to use the package. <a target="_blank" href="https://colab.research.google.com/github/ZenGuard-AI/zenguard-benchmarks/blob/main/assets/colabs/zenguard-benchmarks.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>


#### Benchmarking Output

## Zen Bench

## More information

A much more detailed documentation is available at [docs.zenguard.ai](https://docs.zenguard.ai/).

Test the capabilities of ZenGuard AI in our ZenGuard [Playground](https://console.zenguard.ai/chat). It's available to start for free to understand how our guardrails can enhance your GenAI applications.

Check out our [Client](https://github.com/ZenGuard-AI/fast-llm-security-guardrails) library to get started with integrating ZenGuard AI into your project.

## Support

[Book a Demo](https://calendly.com/galym-u) or just shoot us an email to hello@zenguard.ai

Topics we care about - LLM Security, LLM Guardrails, Prompt Injections, GenAI Security.

---


<p align="center">Developed with ❤️ by <a href="https://zenguard.ai/">ZenGuard AI</a></p>

