https://github.com/balavenkatesh3322/guardrails-demo
LLM Security Project with Llama Guard
https://github.com/balavenkatesh3322/guardrails-demo
aisecurity attack-defense generative-ai llama-2 llama-guard llm llm-security llmops prompt-injection-tool security
Last synced: about 1 month ago
JSON representation
LLM Security Project with Llama Guard
- Host: GitHub
- URL: https://github.com/balavenkatesh3322/guardrails-demo
- Owner: balavenkatesh3322
- Created: 2024-01-19T11:32:57.000Z (over 1 year ago)
- Default Branch: master
- Last Pushed: 2024-02-18T07:30:46.000Z (over 1 year ago)
- Last Synced: 2025-06-27T02:42:12.028Z (3 months ago)
- Topics: aisecurity, attack-defense, generative-ai, llama-2, llama-guard, llm, llm-security, llmops, prompt-injection-tool, security
- Language: Python
- Homepage:
- Size: 55.7 KB
- Stars: 10
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# LLM Security Project with Llama Guard
This repository provides a quick and easy way to run the Llama Guard application on your local machine and explore LLM security.
## What is Llama Guard?
Llama Guard is a defensive framework designed to detect and mitigate potential security risks associated with Large Language Models (LLMs). It helps developers and researchers build safer and more reliable LLM applications.
## What's included?
Nemo Guardrail Implementation: The llama-guard folder contains a NeMo Guardrail implementation, offering flexibility and customization for your specific needs.
Streamlit Applications: Two Streamlit applications are provided for convenient testing:
llama-guard-only.py: Test input prompts and responses directly with Llama Guard.
llama_2_with_llama-guard.py: Run Llama Guard with the pre-trained Llama 2 13b model for real-world testing.
## How to run the application:
- Clone this repository
- Install dependencies: pip install -r requirements.txt
- Run the desired application:
1. Test Llama Guard: streamlit run llama-guard-only.py
2. Test with Llama 2 13b: streamlit run llama_2_with_llama-guard.py
## Learn More:
Blog post: Deepen your understanding of Llama Guard and LLM security with this informative blog post: https://balavenkatesh.medium.com/securing-tomorrows-ai-world-today-llama-guard-defensive-strategies-for-llm-application-c29a87ba607f